Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4598 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5152. Min Range: -4.5152
Max Act: 4.5152. Min Act: -0.1700
Data Index: 7756257 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5152. Min Range: -4.5152
Max Act: 4.4214. Min Act: -0.1700
Data Index: 4186615 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5152. Min Range: -4.5152
Max Act: 4.4214. Min Act: -0.1700
Data Index: 3993655 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5152. Min Range: -4.5152
Max Act: 4.3902. Min Act: -0.1700
Data Index: 1880279 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5152. Min Range: -4.5152
Max Act: 4.3589. Min Act: -0.1700
Data Index: 6168857 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5152. Min Range: -4.5152
Max Act: 4.3277. Min Act: -0.1700
Data Index: 1352301 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5152. Min Range: -4.5152
Max Act: 4.2964. Min Act: -0.1700
Data Index: 309662 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5152. Min Range: -4.5152
Max Act: 4.2652. Min Act: -0.1700
Data Index: 8289885 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5152. Min Range: -4.5152
Max Act: 4.2652. Min Act: -0.1700
Data Index: 3139240 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5152. Min Range: -4.5152
Max Act: 4.2339. Min Act: -0.1700
Data Index: 1650382 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5152. Min Range: -4.5152
Max Act: 4.2339. Min Act: -0.1700
Data Index: 4761892 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5152. Min Range: -4.5152
Max Act: 4.2339. Min Act: -0.1700
Data Index: 6077332 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5152. Min Range: -4.5152
Max Act: 4.2339. Min Act: -0.1700
Data Index: 4657835 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5152. Min Range: -4.5152
Max Act: 4.2339. Min Act: -0.1700
Data Index: 8107803 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5152. Min Range: -4.5152
Max Act: 4.2027. Min Act: -0.1700
Data Index: 3622447 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5152. Min Range: -4.5152
Max Act: 4.1714. Min Act: -0.1700
Data Index: 6698468 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5152. Min Range: -4.5152
Max Act: 4.1714. Min Act: -0.1700
Data Index: 36946 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5152. Min Range: -4.5152
Max Act: 4.1714. Min Act: -0.1700
Data Index: 5562731 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5152. Min Range: -4.5152
Max Act: 4.1714. Min Act: -0.1700
Data Index: 6027954 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5152. Min Range: -4.5152
Max Act: 4.1714. Min Act: -0.1700
Data Index: 5758087 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #19