Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2783 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.0858. Min Range: -9.0858
Max Act: 9.0858. Min Act: -0.1700
Data Index: 5730132 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0858. Min Range: -9.0858
Max Act: 8.9608. Min Act: -0.1700
Data Index: 8465992 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0858. Min Range: -9.0858
Max Act: 8.8983. Min Act: -0.1700
Data Index: 5730131 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0858. Min Range: -9.0858
Max Act: 8.5233. Min Act: -0.1700
Data Index: 4860442 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0858. Min Range: -9.0858
Max Act: 8.4608. Min Act: -0.1700
Data Index: 6359996 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0858. Min Range: -9.0858
Max Act: 8.5233. Min Act: -0.1700
Data Index: 6359993 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0858. Min Range: -9.0858
Max Act: 8.3983. Min Act: -0.1700
Data Index: 4146433 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0858. Min Range: -9.0858
Max Act: 8.3983. Min Act: -0.1700
Data Index: 2989861 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0858. Min Range: -9.0858
Max Act: 8.3983. Min Act: -0.1700
Data Index: 7841867 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0858. Min Range: -9.0858
Max Act: 8.3358. Min Act: -0.1700
Data Index: 1943349 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0858. Min Range: -9.0858
Max Act: 8.2733. Min Act: -0.1700
Data Index: 3924362 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0858. Min Range: -9.0858
Max Act: 8.2733. Min Act: -0.1700
Data Index: 3282732 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0858. Min Range: -9.0858
Max Act: 8.2733. Min Act: -0.1700
Data Index: 5036025 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0858. Min Range: -9.0858
Max Act: 8.1483. Min Act: -0.1700
Data Index: 313388 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0858. Min Range: -9.0858
Max Act: 8.2108. Min Act: -0.1700
Data Index: 7841865 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0858. Min Range: -9.0858
Max Act: 8.2733. Min Act: -0.1700
Data Index: 288626 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0858. Min Range: -9.0858
Max Act: 8.1483. Min Act: -0.1700
Data Index: 187920 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0858. Min Range: -9.0858
Max Act: 8.1483. Min Act: -0.1700
Data Index: 3543613 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0858. Min Range: -9.0858
Max Act: 8.2108. Min Act: -0.1700
Data Index: 6248524 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0858. Min Range: -9.0858
Max Act: 8.1483. Min Act: -0.1700
Data Index: 933404 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #19