Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3798 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.5235. Min Range: -2.5235
Max Act: 2.5235. Min Act: -0.1700
Data Index: 4394751 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.5235. Min Range: -2.5235
Max Act: 2.4587. Min Act: -0.1700
Data Index: 5624875 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.5235. Min Range: -2.5235
Max Act: 2.4262. Min Act: -0.1700
Data Index: 5724048 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.5235. Min Range: -2.5235
Max Act: 2.3935. Min Act: -0.1700
Data Index: 4397906 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.5235. Min Range: -2.5235
Max Act: 2.3935. Min Act: -0.1700
Data Index: 7592625 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.5235. Min Range: -2.5235
Max Act: 2.3445. Min Act: -0.1700
Data Index: 1912101 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.5235. Min Range: -2.5235
Max Act: 2.3608. Min Act: -0.1700
Data Index: 5098944 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.5235. Min Range: -2.5235
Max Act: 2.3608. Min Act: -0.1700
Data Index: 3501355 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.5235. Min Range: -2.5235
Max Act: 2.3445. Min Act: -0.1700
Data Index: 2787642 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.5235. Min Range: -2.5235
Max Act: 2.3116. Min Act: -0.1700
Data Index: 480160 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.5235. Min Range: -2.5235
Max Act: 2.3116. Min Act: -0.1700
Data Index: 8420280 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.5235. Min Range: -2.5235
Max Act: 2.3281. Min Act: -0.1700
Data Index: 4131091 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.5235. Min Range: -2.5235
Max Act: 2.3281. Min Act: -0.1700
Data Index: 3895793 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.5235. Min Range: -2.5235
Max Act: 2.3116. Min Act: -0.1700
Data Index: 6343494 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.5235. Min Range: -2.5235
Max Act: 2.3281. Min Act: -0.1700
Data Index: 3311397 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.5235. Min Range: -2.5235
Max Act: 2.3281. Min Act: -0.1700
Data Index: 3912970 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.5235. Min Range: -2.5235
Max Act: 2.3116. Min Act: -0.1700
Data Index: 4659878 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.5235. Min Range: -2.5235
Max Act: 2.2952. Min Act: -0.1700
Data Index: 1877904 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.5235. Min Range: -2.5235
Max Act: 2.2952. Min Act: -0.1700
Data Index: 1164453 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.5235. Min Range: -2.5235
Max Act: 2.2952. Min Act: -0.1700
Data Index: 3222827 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #19