Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2943 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6258. Min Range: -3.6258
Max Act: 3.6258. Min Act: -0.1700
Data Index: 22960 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6258. Min Range: -3.6258
Max Act: 3.5789. Min Act: -0.1700
Data Index: 7839676 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6258. Min Range: -3.6258
Max Act: 3.5632. Min Act: -0.1700
Data Index: 7051295 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6258. Min Range: -3.6258
Max Act: 3.4536. Min Act: -0.1700
Data Index: 1611094 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6258. Min Range: -3.6258
Max Act: 3.4222. Min Act: -0.1700
Data Index: 8757913 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6258. Min Range: -3.6258
Max Act: 3.3909. Min Act: -0.1700
Data Index: 2329455 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6258. Min Range: -3.6258
Max Act: 3.4066. Min Act: -0.1700
Data Index: 3866529 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6258. Min Range: -3.6258
Max Act: 3.4379. Min Act: -0.1700
Data Index: 8163038 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6258. Min Range: -3.6258
Max Act: 3.3909. Min Act: -0.1700
Data Index: 5156215 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6258. Min Range: -3.6258
Max Act: 3.3595. Min Act: -0.1700
Data Index: 1735888 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6258. Min Range: -3.6258
Max Act: 3.3281. Min Act: -0.1700
Data Index: 8126859 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6258. Min Range: -3.6258
Max Act: 3.3438. Min Act: -0.1700
Data Index: 5043599 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6258. Min Range: -3.6258
Max Act: 3.3595. Min Act: -0.1700
Data Index: 7335801 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6258. Min Range: -3.6258
Max Act: 3.3595. Min Act: -0.1700
Data Index: 4603765 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6258. Min Range: -3.6258
Max Act: 3.3438. Min Act: -0.1700
Data Index: 4492688 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6258. Min Range: -3.6258
Max Act: 3.3438. Min Act: -0.1700
Data Index: 2239792 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6258. Min Range: -3.6258
Max Act: 3.2496. Min Act: -0.1700
Data Index: 54276 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6258. Min Range: -3.6258
Max Act: 3.2810. Min Act: -0.1700
Data Index: 6460038 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6258. Min Range: -3.6258
Max Act: 3.2810. Min Act: -0.1700
Data Index: 2152711 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6258. Min Range: -3.6258
Max Act: 3.2967. Min Act: -0.1700
Data Index: 4931079 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #19