Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4641 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5165. Min Range: -6.5165
Max Act: 6.5165. Min Act: -0.1700
Data Index: 2798099 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5165. Min Range: -6.5165
Max Act: 6.4228. Min Act: -0.1700
Data Index: 8353878 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5165. Min Range: -6.5165
Max Act: 6.4228. Min Act: -0.1700
Data Index: 1280943 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5165. Min Range: -6.5165
Max Act: 6.4228. Min Act: -0.1700
Data Index: 2655878 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5165. Min Range: -6.5165
Max Act: 6.3915. Min Act: -0.1700
Data Index: 7587491 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5165. Min Range: -6.5165
Max Act: 6.3290. Min Act: -0.1700
Data Index: 470490 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5165. Min Range: -6.5165
Max Act: 6.3290. Min Act: -0.1700
Data Index: 7856226 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5165. Min Range: -6.5165
Max Act: 6.2665. Min Act: -0.1700
Data Index: 6440880 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5165. Min Range: -6.5165
Max Act: 6.2978. Min Act: -0.1700
Data Index: 1548261 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5165. Min Range: -6.5165
Max Act: 6.2978. Min Act: -0.1700
Data Index: 7819121 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5165. Min Range: -6.5165
Max Act: 6.2665. Min Act: -0.1700
Data Index: 6019384 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5165. Min Range: -6.5165
Max Act: 6.2665. Min Act: -0.1700
Data Index: 7461305 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5165. Min Range: -6.5165
Max Act: 6.2040. Min Act: -0.1700
Data Index: 8296756 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5165. Min Range: -6.5165
Max Act: 6.2353. Min Act: -0.1700
Data Index: 1090729 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5165. Min Range: -6.5165
Max Act: 6.2040. Min Act: -0.1700
Data Index: 4331809 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5165. Min Range: -6.5165
Max Act: 6.1728. Min Act: -0.1700
Data Index: 5405409 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5165. Min Range: -6.5165
Max Act: 6.1728. Min Act: -0.1700
Data Index: 48976 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5165. Min Range: -6.5165
Max Act: 6.1728. Min Act: -0.1700
Data Index: 2331545 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5165. Min Range: -6.5165
Max Act: 6.1728. Min Act: -0.1700
Data Index: 129283 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5165. Min Range: -6.5165
Max Act: 6.1415. Min Act: -0.1700
Data Index: 3471652 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19