Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1413 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6379. Min Range: -5.6379
Max Act: 5.6379. Min Act: -0.1700
Data Index: 2799984 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6379. Min Range: -5.6379
Max Act: 5.5441. Min Act: -0.1700
Data Index: 7902592 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6379. Min Range: -5.6379
Max Act: 5.5441. Min Act: -0.1700
Data Index: 3151567 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6379. Min Range: -5.6379
Max Act: 5.4816. Min Act: -0.1700
Data Index: 2334063 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6379. Min Range: -5.6379
Max Act: 5.4191. Min Act: -0.1700
Data Index: 7255952 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6379. Min Range: -5.6379
Max Act: 5.4504. Min Act: -0.1700
Data Index: 7404429 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6379. Min Range: -5.6379
Max Act: 5.4504. Min Act: -0.1700
Data Index: 8099033 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6379. Min Range: -5.6379
Max Act: 5.4504. Min Act: -0.1700
Data Index: 1860927 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6379. Min Range: -5.6379
Max Act: 5.4191. Min Act: -0.1700
Data Index: 143296 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6379. Min Range: -5.6379
Max Act: 5.4191. Min Act: -0.1700
Data Index: 3160282 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6379. Min Range: -5.6379
Max Act: 5.4504. Min Act: -0.1700
Data Index: 6217557 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6379. Min Range: -5.6379
Max Act: 5.4191. Min Act: -0.1700
Data Index: 4206932 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6379. Min Range: -5.6379
Max Act: 5.4191. Min Act: -0.1700
Data Index: 1566533 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6379. Min Range: -5.6379
Max Act: 5.4191. Min Act: -0.1700
Data Index: 3721308 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6379. Min Range: -5.6379
Max Act: 5.3254. Min Act: -0.1700
Data Index: 4149311 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6379. Min Range: -5.6379
Max Act: 5.3254. Min Act: -0.1700
Data Index: 7837646 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6379. Min Range: -5.6379
Max Act: 5.3566. Min Act: -0.1700
Data Index: 7411425 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6379. Min Range: -5.6379
Max Act: 5.3254. Min Act: -0.1700
Data Index: 7997632 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6379. Min Range: -5.6379
Max Act: 5.2941. Min Act: -0.1700
Data Index: 7599618 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6379. Min Range: -5.6379
Max Act: 5.2941. Min Act: -0.1700
Data Index: 2371665 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #19