Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3342 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7845. Min Range: -5.7845
Max Act: 5.7845. Min Act: -0.1700
Data Index: 4198120 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7845. Min Range: -5.7845
Max Act: 5.7845. Min Act: -0.1700
Data Index: 1276875 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7845. Min Range: -5.7845
Max Act: 5.6595. Min Act: -0.1700
Data Index: 2362817 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7845. Min Range: -5.7845
Max Act: 5.5345. Min Act: -0.1700
Data Index: 1845969 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7845. Min Range: -5.7845
Max Act: 5.5657. Min Act: -0.1700
Data Index: 7677695 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7845. Min Range: -5.7845
Max Act: 5.5032. Min Act: -0.1700
Data Index: 3496965 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7845. Min Range: -5.7845
Max Act: 5.4407. Min Act: -0.1700
Data Index: 5558721 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7845. Min Range: -5.7845
Max Act: 5.4407. Min Act: -0.1700
Data Index: 5201870 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7845. Min Range: -5.7845
Max Act: 5.3782. Min Act: -0.1700
Data Index: 4158402 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7845. Min Range: -5.7845
Max Act: 5.3782. Min Act: -0.1700
Data Index: 3330791 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7845. Min Range: -5.7845
Max Act: 5.3157. Min Act: -0.1700
Data Index: 500882 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7845. Min Range: -5.7845
Max Act: 5.3470. Min Act: -0.1700
Data Index: 3601323 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7845. Min Range: -5.7845
Max Act: 5.3157. Min Act: -0.1700
Data Index: 8758191 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7845. Min Range: -5.7845
Max Act: 5.3157. Min Act: -0.1700
Data Index: 7349471 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7845. Min Range: -5.7845
Max Act: 5.2845. Min Act: -0.1700
Data Index: 4141860 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7845. Min Range: -5.7845
Max Act: 5.3157. Min Act: -0.1700
Data Index: 2425584 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7845. Min Range: -5.7845
Max Act: 5.3157. Min Act: -0.1700
Data Index: 3402395 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7845. Min Range: -5.7845
Max Act: 5.2845. Min Act: -0.1700
Data Index: 2916969 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7845. Min Range: -5.7845
Max Act: 5.2845. Min Act: -0.1700
Data Index: 606054 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7845. Min Range: -5.7845
Max Act: 5.2532. Min Act: -0.1700
Data Index: 3493660 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #19