Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2455 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.0544. Min Range: -11.0544
Max Act: 11.0544. Min Act: -0.1700
Data Index: 7636831 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.0544. Min Range: -11.0544
Max Act: 10.9294. Min Act: -0.1700
Data Index: 6099318 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.0544. Min Range: -11.0544
Max Act: 10.9294. Min Act: -0.1700
Data Index: 1939658 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.0544. Min Range: -11.0544
Max Act: 10.9294. Min Act: -0.1700
Data Index: 6099316 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.0544. Min Range: -11.0544
Max Act: 10.8669. Min Act: -0.1700
Data Index: 8457079 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.0544. Min Range: -11.0544
Max Act: 10.9294. Min Act: -0.1700
Data Index: 6099306 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.0544. Min Range: -11.0544
Max Act: 10.8044. Min Act: -0.1700
Data Index: 1939661 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.0544. Min Range: -11.0544
Max Act: 10.8044. Min Act: -0.1700
Data Index: 7636833 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.0544. Min Range: -11.0544
Max Act: 10.6794. Min Act: -0.1700
Data Index: 8335027 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.0544. Min Range: -11.0544
Max Act: 10.6169. Min Act: -0.1700
Data Index: 4404701 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.0544. Min Range: -11.0544
Max Act: 10.5544. Min Act: -0.1700
Data Index: 1939654 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.0544. Min Range: -11.0544
Max Act: 10.5544. Min Act: -0.1700
Data Index: 4142379 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.0544. Min Range: -11.0544
Max Act: 10.4919. Min Act: -0.1700
Data Index: 6995783 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.0544. Min Range: -11.0544
Max Act: 10.3669. Min Act: -0.1700
Data Index: 3927047 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.0544. Min Range: -11.0544
Max Act: 10.3669. Min Act: -0.1700
Data Index: 8778897 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.0544. Min Range: -11.0544
Max Act: 10.3044. Min Act: -0.1700
Data Index: 5335145 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.0544. Min Range: -11.0544
Max Act: 10.3044. Min Act: -0.1700
Data Index: 2512199 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.0544. Min Range: -11.0544
Max Act: 10.3044. Min Act: -0.1700
Data Index: 2446249 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.0544. Min Range: -11.0544
Max Act: 10.3044. Min Act: -0.1700
Data Index: 1939657 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.0544. Min Range: -11.0544
Max Act: 10.3044. Min Act: -0.1700
Data Index: 1939649 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #19