Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3823 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8140. Min Range: -5.8140
Max Act: 5.8140. Min Act: -0.1700
Data Index: 2136201 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8140. Min Range: -5.8140
Max Act: 5.7515. Min Act: -0.1700
Data Index: 5891219 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8140. Min Range: -5.8140
Max Act: 5.7515. Min Act: -0.1700
Data Index: 4914037 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8140. Min Range: -5.8140
Max Act: 5.7202. Min Act: -0.1700
Data Index: 3582360 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8140. Min Range: -5.8140
Max Act: 5.7515. Min Act: -0.1700
Data Index: 7098407 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8140. Min Range: -5.8140
Max Act: 5.7202. Min Act: -0.1700
Data Index: 2829654 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8140. Min Range: -5.8140
Max Act: 5.6890. Min Act: -0.1700
Data Index: 8721845 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8140. Min Range: -5.8140
Max Act: 5.6890. Min Act: -0.1700
Data Index: 1660347 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8140. Min Range: -5.8140
Max Act: 5.6577. Min Act: -0.1700
Data Index: 7382735 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8140. Min Range: -5.8140
Max Act: 5.6577. Min Act: -0.1700
Data Index: 6658847 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8140. Min Range: -5.8140
Max Act: 5.6577. Min Act: -0.1700
Data Index: 3620192 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8140. Min Range: -5.8140
Max Act: 5.6890. Min Act: -0.1700
Data Index: 8775486 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8140. Min Range: -5.8140
Max Act: 5.6265. Min Act: -0.1700
Data Index: 3423033 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8140. Min Range: -5.8140
Max Act: 5.5952. Min Act: -0.1699
Data Index: 3586474 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8140. Min Range: -5.8140
Max Act: 5.6265. Min Act: -0.1700
Data Index: 5412161 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8140. Min Range: -5.8140
Max Act: 5.6265. Min Act: -0.1700
Data Index: 303598 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8140. Min Range: -5.8140
Max Act: 5.6265. Min Act: -0.1700
Data Index: 4177467 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8140. Min Range: -5.8140
Max Act: 5.6265. Min Act: -0.1700
Data Index: 4328734 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8140. Min Range: -5.8140
Max Act: 5.5952. Min Act: -0.1700
Data Index: 4048559 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8140. Min Range: -5.8140
Max Act: 5.5952. Min Act: -0.1700
Data Index: 5665230 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #19