Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4819 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6362. Min Range: -3.6362
Max Act: 3.6362. Min Act: -0.1700
Data Index: 2025175 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6362. Min Range: -3.6362
Max Act: 3.5893. Min Act: -0.1700
Data Index: 3186276 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6362. Min Range: -3.6362
Max Act: 3.5580. Min Act: -0.1700
Data Index: 2927653 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6362. Min Range: -3.6362
Max Act: 3.5580. Min Act: -0.1700
Data Index: 2507650 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6362. Min Range: -3.6362
Max Act: 3.5110. Min Act: -0.1700
Data Index: 4656063 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6362. Min Range: -3.6362
Max Act: 3.5267. Min Act: -0.1700
Data Index: 1888409 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6362. Min Range: -3.6362
Max Act: 3.5110. Min Act: -0.1700
Data Index: 5956904 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6362. Min Range: -3.6362
Max Act: 3.5110. Min Act: -0.1700
Data Index: 4083930 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6362. Min Range: -3.6362
Max Act: 3.5267. Min Act: -0.1700
Data Index: 4886553 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6362. Min Range: -3.6362
Max Act: 3.4954. Min Act: -0.1700
Data Index: 1063994 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6362. Min Range: -3.6362
Max Act: 3.4954. Min Act: -0.1700
Data Index: 5446200 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6362. Min Range: -3.6362
Max Act: 3.4484. Min Act: -0.1700
Data Index: 3279098 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6362. Min Range: -3.6362
Max Act: 3.4484. Min Act: -0.1700
Data Index: 5186105 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6362. Min Range: -3.6362
Max Act: 3.4484. Min Act: -0.1700
Data Index: 2131956 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6362. Min Range: -3.6362
Max Act: 3.4484. Min Act: -0.1700
Data Index: 1509134 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6362. Min Range: -3.6362
Max Act: 3.4170. Min Act: -0.1700
Data Index: 598256 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6362. Min Range: -3.6362
Max Act: 3.4484. Min Act: -0.1700
Data Index: 5299719 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6362. Min Range: -3.6362
Max Act: 3.4327. Min Act: -0.1700
Data Index: 3398088 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6362. Min Range: -3.6362
Max Act: 3.4327. Min Act: -0.1700
Data Index: 1559276 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6362. Min Range: -3.6362
Max Act: 3.4170. Min Act: -0.1700
Data Index: 2483818 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #19