Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3538 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9483. Min Range: -5.9483
Max Act: 5.9483. Min Act: -0.1700
Data Index: 3548605 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9483. Min Range: -5.9483
Max Act: 5.9171. Min Act: -0.1700
Data Index: 91757 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9483. Min Range: -5.9483
Max Act: 5.9171. Min Act: -0.1700
Data Index: 5771919 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9483. Min Range: -5.9483
Max Act: 5.8233. Min Act: -0.1700
Data Index: 7491313 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9483. Min Range: -5.9483
Max Act: 5.7921. Min Act: -0.1700
Data Index: 8587014 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9483. Min Range: -5.9483
Max Act: 5.7296. Min Act: -0.1700
Data Index: 2691029 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9483. Min Range: -5.9483
Max Act: 5.7296. Min Act: -0.1700
Data Index: 4791144 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9483. Min Range: -5.9483
Max Act: 5.7296. Min Act: -0.1700
Data Index: 2189782 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9483. Min Range: -5.9483
Max Act: 5.6671. Min Act: -0.1700
Data Index: 5274829 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9483. Min Range: -5.9483
Max Act: 5.6671. Min Act: -0.1700
Data Index: 5336290 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9483. Min Range: -5.9483
Max Act: 5.6671. Min Act: -0.1700
Data Index: 3839596 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9483. Min Range: -5.9483
Max Act: 5.6671. Min Act: -0.1700
Data Index: 4858266 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9483. Min Range: -5.9483
Max Act: 5.6671. Min Act: -0.1700
Data Index: 3412776 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9483. Min Range: -5.9483
Max Act: 5.6671. Min Act: -0.1700
Data Index: 3984143 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9483. Min Range: -5.9483
Max Act: 5.6671. Min Act: -0.1700
Data Index: 6574552 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9483. Min Range: -5.9483
Max Act: 5.6671. Min Act: -0.1700
Data Index: 190744 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9483. Min Range: -5.9483
Max Act: 5.6358. Min Act: -0.1700
Data Index: 4844965 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9483. Min Range: -5.9483
Max Act: 5.6671. Min Act: -0.1700
Data Index: 6215052 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9483. Min Range: -5.9483
Max Act: 5.6358. Min Act: -0.1700
Data Index: 8809346 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9483. Min Range: -5.9483
Max Act: 5.6046. Min Act: -0.1700
Data Index: 4350635 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #19