Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3635 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 11.1439. Min Range: -11.1439
Max Act: 11.1439. Min Act: -0.1700
Data Index: 7564733 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 11.1439. Min Range: -11.1439
Max Act: 11.0189. Min Act: -0.1700
Data Index: 1823261 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 11.1439. Min Range: -11.1439
Max Act: 10.7689. Min Act: -0.1700
Data Index: 2602387 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 11.1439. Min Range: -11.1439
Max Act: 10.3939. Min Act: -0.1699
Data Index: 5672575 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 11.1439. Min Range: -11.1439
Max Act: 10.3939. Min Act: -0.1700
Data Index: 7980722 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 11.1439. Min Range: -11.1439
Max Act: 10.3939. Min Act: -0.1700
Data Index: 2506871 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 11.1439. Min Range: -11.1439
Max Act: 10.3939. Min Act: -0.1700
Data Index: 6556286 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 11.1439. Min Range: -11.1439
Max Act: 10.2689. Min Act: -0.1700
Data Index: 7520102 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 11.1439. Min Range: -11.1439
Max Act: 10.1439. Min Act: -0.1700
Data Index: 290488 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 11.1439. Min Range: -11.1439
Max Act: 10.0814. Min Act: -0.1700
Data Index: 3014059 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 11.1439. Min Range: -11.1439
Max Act: 10.0189. Min Act: -0.1700
Data Index: 1828042 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 11.1439. Min Range: -11.1439
Max Act: 10.0189. Min Act: -0.1700
Data Index: 3737837 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 11.1439. Min Range: -11.1439
Max Act: 10.0189. Min Act: -0.1700
Data Index: 1739738 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 11.1439. Min Range: -11.1439
Max Act: 9.9564. Min Act: -0.1700
Data Index: 7374434 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 11.1439. Min Range: -11.1439
Max Act: 9.9564. Min Act: -0.1700
Data Index: 5583512 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 11.1439. Min Range: -11.1439
Max Act: 9.8939. Min Act: -0.1700
Data Index: 7725718 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 11.1439. Min Range: -11.1439
Max Act: 9.8939. Min Act: -0.1700
Data Index: 2729271 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 11.1439. Min Range: -11.1439
Max Act: 9.8939. Min Act: -0.1700
Data Index: 7570244 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 11.1439. Min Range: -11.1439
Max Act: 9.8939. Min Act: -0.1700
Data Index: 2281459 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 11.1439. Min Range: -11.1439
Max Act: 9.8314. Min Act: -0.1700
Data Index: 268866 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #19