Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 996 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 4.4086. Min Range: -4.4086
Max Act: 4.4086. Min Act: -0.1700
Data Index: 4571604 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4086. Min Range: -4.4086
Max Act: 4.3149. Min Act: -0.1700
Data Index: 1301438 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4086. Min Range: -4.4086
Max Act: 4.2211. Min Act: -0.1700
Data Index: 6689881 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4086. Min Range: -4.4086
Max Act: 4.2211. Min Act: -0.1700
Data Index: 7391696 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4086. Min Range: -4.4086
Max Act: 4.0648. Min Act: -0.1700
Data Index: 4333841 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4086. Min Range: -4.4086
Max Act: 4.0648. Min Act: -0.1700
Data Index: 6417218 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4086. Min Range: -4.4086
Max Act: 4.0961. Min Act: -0.1700
Data Index: 5282755 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4086. Min Range: -4.4086
Max Act: 4.0961. Min Act: -0.1700
Data Index: 2138922 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4086. Min Range: -4.4086
Max Act: 4.0961. Min Act: -0.1700
Data Index: 8304866 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4086. Min Range: -4.4086
Max Act: 4.0648. Min Act: -0.1700
Data Index: 6019589 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4086. Min Range: -4.4086
Max Act: 4.0023. Min Act: -0.1700
Data Index: 8202661 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4086. Min Range: -4.4086
Max Act: 4.0023. Min Act: -0.1700
Data Index: 214595 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4086. Min Range: -4.4086
Max Act: 4.0336. Min Act: -0.1700
Data Index: 668632 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4086. Min Range: -4.4086
Max Act: 4.0336. Min Act: -0.1700
Data Index: 8265301 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4086. Min Range: -4.4086
Max Act: 4.0648. Min Act: -0.1700
Data Index: 6814311 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4086. Min Range: -4.4086
Max Act: 4.0336. Min Act: -0.1700
Data Index: 2885333 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4086. Min Range: -4.4086
Max Act: 4.0023. Min Act: -0.1700
Data Index: 7566036 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4086. Min Range: -4.4086
Max Act: 3.9711. Min Act: -0.1700
Data Index: 3813652 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4086. Min Range: -4.4086
Max Act: 4.0023. Min Act: -0.1700
Data Index: 4652373 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4086. Min Range: -4.4086
Max Act: 4.0648. Min Act: -0.1700
Data Index: 4606467 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #19