Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3315 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0354. Min Range: -6.0354
Max Act: 6.0354. Min Act: -0.1700
Data Index: 3605290 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0354. Min Range: -6.0354
Max Act: 5.5979. Min Act: -0.1700
Data Index: 7367678 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0354. Min Range: -6.0354
Max Act: 5.5042. Min Act: -0.1700
Data Index: 8716372 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0354. Min Range: -6.0354
Max Act: 5.4104. Min Act: -0.1700
Data Index: 4353455 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0354. Min Range: -6.0354
Max Act: 5.3792. Min Act: -0.1700
Data Index: 1223212 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0354. Min Range: -6.0354
Max Act: 5.3479. Min Act: -0.1700
Data Index: 4095361 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0354. Min Range: -6.0354
Max Act: 5.3792. Min Act: -0.1700
Data Index: 5322755 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0354. Min Range: -6.0354
Max Act: 5.3167. Min Act: -0.1700
Data Index: 3031429 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0354. Min Range: -6.0354
Max Act: 5.2854. Min Act: -0.1700
Data Index: 5594048 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0354. Min Range: -6.0354
Max Act: 5.2854. Min Act: -0.1700
Data Index: 1233320 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0354. Min Range: -6.0354
Max Act: 5.2854. Min Act: -0.1700
Data Index: 5039365 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0354. Min Range: -6.0354
Max Act: 5.2854. Min Act: -0.1700
Data Index: 4177105 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0354. Min Range: -6.0354
Max Act: 5.2854. Min Act: -0.1700
Data Index: 7233187 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0354. Min Range: -6.0354
Max Act: 5.2542. Min Act: -0.1700
Data Index: 2728140 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0354. Min Range: -6.0354
Max Act: 5.2542. Min Act: -0.1700
Data Index: 5637486 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0354. Min Range: -6.0354
Max Act: 5.2229. Min Act: -0.1700
Data Index: 369164 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0354. Min Range: -6.0354
Max Act: 5.2542. Min Act: -0.1700
Data Index: 4090328 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0354. Min Range: -6.0354
Max Act: 5.1917. Min Act: -0.1700
Data Index: 587327 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0354. Min Range: -6.0354
Max Act: 5.1917. Min Act: -0.1700
Data Index: 990549 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0354. Min Range: -6.0354
Max Act: 5.1917. Min Act: -0.1700
Data Index: 197030 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19