Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5117 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2726. Min Range: -5.2726
Max Act: 5.2726. Min Act: -0.1700
Data Index: 5250140 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2726. Min Range: -5.2726
Max Act: 5.2726. Min Act: -0.1700
Data Index: 1977904 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2726. Min Range: -5.2726
Max Act: 5.2101. Min Act: -0.1700
Data Index: 16208 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2726. Min Range: -5.2726
Max Act: 5.1788. Min Act: -0.1700
Data Index: 6518454 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2726. Min Range: -5.2726
Max Act: 5.1476. Min Act: -0.1700
Data Index: 7081509 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2726. Min Range: -5.2726
Max Act: 5.0538. Min Act: -0.1700
Data Index: 2599663 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2726. Min Range: -5.2726
Max Act: 5.0851. Min Act: -0.1700
Data Index: 3148527 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2726. Min Range: -5.2726
Max Act: 5.0538. Min Act: -0.1700
Data Index: 7010963 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2726. Min Range: -5.2726
Max Act: 5.0538. Min Act: -0.1700
Data Index: 8300065 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2726. Min Range: -5.2726
Max Act: 5.0538. Min Act: -0.1700
Data Index: 5203214 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2726. Min Range: -5.2726
Max Act: 5.0226. Min Act: -0.1700
Data Index: 7178695 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2726. Min Range: -5.2726
Max Act: 5.0226. Min Act: -0.1700
Data Index: 3000268 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2726. Min Range: -5.2726
Max Act: 4.9913. Min Act: -0.1700
Data Index: 6861525 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2726. Min Range: -5.2726
Max Act: 5.0226. Min Act: -0.1700
Data Index: 3441816 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2726. Min Range: -5.2726
Max Act: 5.0226. Min Act: -0.1700
Data Index: 7222683 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2726. Min Range: -5.2726
Max Act: 4.9913. Min Act: -0.1700
Data Index: 154638 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2726. Min Range: -5.2726
Max Act: 4.9913. Min Act: -0.1700
Data Index: 4749492 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2726. Min Range: -5.2726
Max Act: 4.9913. Min Act: -0.1700
Data Index: 5636601 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2726. Min Range: -5.2726
Max Act: 4.9288. Min Act: -0.1700
Data Index: 4774408 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2726. Min Range: -5.2726
Max Act: 4.9601. Min Act: -0.1700
Data Index: 1398644 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #19