Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3445 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0439. Min Range: -9.0439
Max Act: 9.0439. Min Act: -0.1700
Data Index: 8600563 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0439. Min Range: -9.0439
Max Act: 8.9189. Min Act: -0.1700
Data Index: 2212964 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0439. Min Range: -9.0439
Max Act: 8.6689. Min Act: -0.1700
Data Index: 5499982 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0439. Min Range: -9.0439
Max Act: 8.6064. Min Act: -0.1700
Data Index: 4171488 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0439. Min Range: -9.0439
Max Act: 8.6064. Min Act: -0.1700
Data Index: 5240456 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0439. Min Range: -9.0439
Max Act: 8.5439. Min Act: -0.1700
Data Index: 7991793 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0439. Min Range: -9.0439
Max Act: 8.5439. Min Act: -0.1700
Data Index: 1178423 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0439. Min Range: -9.0439
Max Act: 8.5439. Min Act: -0.1700
Data Index: 4560056 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0439. Min Range: -9.0439
Max Act: 8.4814. Min Act: -0.1700
Data Index: 1609339 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0439. Min Range: -9.0439
Max Act: 8.4189. Min Act: -0.1700
Data Index: 852136 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0439. Min Range: -9.0439
Max Act: 8.2939. Min Act: -0.1700
Data Index: 6906945 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0439. Min Range: -9.0439
Max Act: 8.2939. Min Act: -0.1700
Data Index: 3193053 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0439. Min Range: -9.0439
Max Act: 8.2939. Min Act: -0.1700
Data Index: 8004617 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0439. Min Range: -9.0439
Max Act: 8.2939. Min Act: -0.1700
Data Index: 329514 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0439. Min Range: -9.0439
Max Act: 8.2314. Min Act: -0.1700
Data Index: 4079000 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0439. Min Range: -9.0439
Max Act: 8.2314. Min Act: -0.1700
Data Index: 4126884 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0439. Min Range: -9.0439
Max Act: 8.2314. Min Act: -0.1700
Data Index: 6881936 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0439. Min Range: -9.0439
Max Act: 8.1689. Min Act: -0.1700
Data Index: 1374475 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0439. Min Range: -9.0439
Max Act: 8.2314. Min Act: -0.1700
Data Index: 1806 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0439. Min Range: -9.0439
Max Act: 8.2314. Min Act: -0.1700
Data Index: 7671582 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #19