Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4327 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5582. Min Range: -5.5582
Max Act: 5.5582. Min Act: -0.1700
Data Index: 7056756 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5582. Min Range: -5.5582
Max Act: 5.5270. Min Act: -0.1700
Data Index: 6435464 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5582. Min Range: -5.5582
Max Act: 5.4645. Min Act: -0.1700
Data Index: 2900971 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5582. Min Range: -5.5582
Max Act: 5.4332. Min Act: -0.1700
Data Index: 5358430 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5582. Min Range: -5.5582
Max Act: 5.4020. Min Act: -0.1700
Data Index: 7961689 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5582. Min Range: -5.5582
Max Act: 5.4020. Min Act: -0.1700
Data Index: 7374797 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5582. Min Range: -5.5582
Max Act: 5.4020. Min Act: -0.1700
Data Index: 849519 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5582. Min Range: -5.5582
Max Act: 5.4020. Min Act: -0.1700
Data Index: 6942701 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5582. Min Range: -5.5582
Max Act: 5.4020. Min Act: -0.1700
Data Index: 4074678 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5582. Min Range: -5.5582
Max Act: 5.4020. Min Act: -0.1700
Data Index: 26037 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5582. Min Range: -5.5582
Max Act: 5.3707. Min Act: -0.1700
Data Index: 6095171 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5582. Min Range: -5.5582
Max Act: 5.3707. Min Act: -0.1700
Data Index: 1155180 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5582. Min Range: -5.5582
Max Act: 5.3395. Min Act: -0.1700
Data Index: 871601 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5582. Min Range: -5.5582
Max Act: 5.3395. Min Act: -0.1700
Data Index: 3303596 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5582. Min Range: -5.5582
Max Act: 5.3082. Min Act: -0.1700
Data Index: 4458216 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5582. Min Range: -5.5582
Max Act: 5.3082. Min Act: -0.1700
Data Index: 1961085 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5582. Min Range: -5.5582
Max Act: 5.3082. Min Act: -0.1700
Data Index: 6101543 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5582. Min Range: -5.5582
Max Act: 5.2770. Min Act: -0.1700
Data Index: 225527 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5582. Min Range: -5.5582
Max Act: 5.2770. Min Act: -0.1700
Data Index: 6486024 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5582. Min Range: -5.5582
Max Act: 5.2770. Min Act: -0.1700
Data Index: 4623265 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #19