Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4457 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4010. Min Range: -5.4010
Max Act: 5.4010. Min Act: -0.1700
Data Index: 2175655 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4010. Min Range: -5.4010
Max Act: 5.3385. Min Act: -0.1700
Data Index: 6280738 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4010. Min Range: -5.4010
Max Act: 5.2447. Min Act: -0.1700
Data Index: 4146114 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4010. Min Range: -5.4010
Max Act: 5.2135. Min Act: -0.1700
Data Index: 7354315 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4010. Min Range: -5.4010
Max Act: 5.1822. Min Act: -0.1700
Data Index: 5030127 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4010. Min Range: -5.4010
Max Act: 5.1510. Min Act: -0.1700
Data Index: 5744789 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4010. Min Range: -5.4010
Max Act: 5.1197. Min Act: -0.1700
Data Index: 111898 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4010. Min Range: -5.4010
Max Act: 5.1197. Min Act: -0.1700
Data Index: 7815200 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4010. Min Range: -5.4010
Max Act: 5.0572. Min Act: -0.1700
Data Index: 3738161 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4010. Min Range: -5.4010
Max Act: 5.0260. Min Act: -0.1700
Data Index: 3738157 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4010. Min Range: -5.4010
Max Act: 5.0260. Min Act: -0.1700
Data Index: 3738150 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4010. Min Range: -5.4010
Max Act: 5.0260. Min Act: -0.1700
Data Index: 7819237 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4010. Min Range: -5.4010
Max Act: 5.0260. Min Act: -0.1700
Data Index: 1433226 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4010. Min Range: -5.4010
Max Act: 4.9947. Min Act: -0.1700
Data Index: 8006878 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4010. Min Range: -5.4010
Max Act: 4.9947. Min Act: -0.1700
Data Index: 3095283 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4010. Min Range: -5.4010
Max Act: 4.9947. Min Act: -0.1700
Data Index: 2631703 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4010. Min Range: -5.4010
Max Act: 4.9947. Min Act: -0.1700
Data Index: 2373074 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4010. Min Range: -5.4010
Max Act: 4.9635. Min Act: -0.1700
Data Index: 2248419 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4010. Min Range: -5.4010
Max Act: 4.9322. Min Act: -0.1700
Data Index: 2057652 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4010. Min Range: -5.4010
Max Act: 4.9635. Min Act: -0.1700
Data Index: 4318677 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #19