Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3429 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4537. Min Range: -7.4537
Max Act: 7.4537. Min Act: -0.1700
Data Index: 6545455 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4537. Min Range: -7.4537
Max Act: 7.1100. Min Act: -0.1700
Data Index: 4369967 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4537. Min Range: -7.4537
Max Act: 6.9537. Min Act: -0.1700
Data Index: 6200259 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4537. Min Range: -7.4537
Max Act: 6.8912. Min Act: -0.1700
Data Index: 5995062 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4537. Min Range: -7.4537
Max Act: 6.8287. Min Act: -0.1700
Data Index: 3567286 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4537. Min Range: -7.4537
Max Act: 6.7037. Min Act: -0.1700
Data Index: 4210689 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4537. Min Range: -7.4537
Max Act: 6.7037. Min Act: -0.1700
Data Index: 1913449 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4537. Min Range: -7.4537
Max Act: 6.6725. Min Act: -0.1700
Data Index: 3640138 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4537. Min Range: -7.4537
Max Act: 6.6725. Min Act: -0.1700
Data Index: 4544180 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4537. Min Range: -7.4537
Max Act: 6.6412. Min Act: -0.1700
Data Index: 8269636 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4537. Min Range: -7.4537
Max Act: 6.6100. Min Act: -0.1700
Data Index: 5198386 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4537. Min Range: -7.4537
Max Act: 6.5162. Min Act: -0.1700
Data Index: 1201642 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4537. Min Range: -7.4537
Max Act: 6.5162. Min Act: -0.1700
Data Index: 7936747 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4537. Min Range: -7.4537
Max Act: 6.4850. Min Act: -0.1700
Data Index: 8706344 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4537. Min Range: -7.4537
Max Act: 6.4850. Min Act: -0.1700
Data Index: 272245 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4537. Min Range: -7.4537
Max Act: 6.4850. Min Act: -0.1700
Data Index: 6260028 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4537. Min Range: -7.4537
Max Act: 6.4537. Min Act: -0.1700
Data Index: 870030 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4537. Min Range: -7.4537
Max Act: 6.4225. Min Act: -0.1700
Data Index: 6442937 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4537. Min Range: -7.4537
Max Act: 6.4225. Min Act: -0.1700
Data Index: 5162205 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4537. Min Range: -7.4537
Max Act: 6.4225. Min Act: -0.1700
Data Index: 1617417 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #19