Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 977 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8146. Min Range: -6.8146
Max Act: 6.8146. Min Act: -0.1700
Data Index: 408693 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8146. Min Range: -6.8146
Max Act: 6.0333. Min Act: -0.1700
Data Index: 826248 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8146. Min Range: -6.8146
Max Act: 5.9708. Min Act: -0.1700
Data Index: 783707 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8146. Min Range: -6.8146
Max Act: 6.0021. Min Act: -0.1700
Data Index: 2408363 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8146. Min Range: -6.8146
Max Act: 5.9708. Min Act: -0.1700
Data Index: 4361986 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8146. Min Range: -6.8146
Max Act: 5.9708. Min Act: -0.1700
Data Index: 4018357 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8146. Min Range: -6.8146
Max Act: 5.8771. Min Act: -0.1700
Data Index: 6281895 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8146. Min Range: -6.8146
Max Act: 5.8771. Min Act: -0.1700
Data Index: 8383646 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8146. Min Range: -6.8146
Max Act: 5.9083. Min Act: -0.1700
Data Index: 6672403 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8146. Min Range: -6.8146
Max Act: 5.8146. Min Act: -0.1700
Data Index: 3455059 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8146. Min Range: -6.8146
Max Act: 5.8146. Min Act: -0.1700
Data Index: 4367079 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8146. Min Range: -6.8146
Max Act: 5.7833. Min Act: -0.1700
Data Index: 8139190 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8146. Min Range: -6.8146
Max Act: 5.7208. Min Act: -0.1700
Data Index: 5965664 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8146. Min Range: -6.8146
Max Act: 5.7521. Min Act: -0.1700
Data Index: 4943535 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8146. Min Range: -6.8146
Max Act: 5.7208. Min Act: -0.1700
Data Index: 770429 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8146. Min Range: -6.8146
Max Act: 5.7208. Min Act: -0.1700
Data Index: 3229643 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8146. Min Range: -6.8146
Max Act: 5.7208. Min Act: -0.1700
Data Index: 6390558 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8146. Min Range: -6.8146
Max Act: 5.7208. Min Act: -0.1700
Data Index: 5739773 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8146. Min Range: -6.8146
Max Act: 5.6896. Min Act: -0.1700
Data Index: 2144022 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8146. Min Range: -6.8146
Max Act: 5.7208. Min Act: -0.1700
Data Index: 2441716 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #19