Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1643 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9484. Min Range: -6.9484
Max Act: 6.9484. Min Act: -0.1700
Data Index: 6207466 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9484. Min Range: -6.9484
Max Act: 6.8546. Min Act: -0.1700
Data Index: 3917406 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9484. Min Range: -6.9484
Max Act: 6.7609. Min Act: -0.1700
Data Index: 7059300 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9484. Min Range: -6.9484
Max Act: 6.7296. Min Act: -0.1700
Data Index: 3058481 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9484. Min Range: -6.9484
Max Act: 6.4796. Min Act: -0.1700
Data Index: 146528 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9484. Min Range: -6.9484
Max Act: 6.3859. Min Act: -0.1700
Data Index: 3408815 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9484. Min Range: -6.9484
Max Act: 6.3546. Min Act: -0.1700
Data Index: 4043765 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9484. Min Range: -6.9484
Max Act: 6.3234. Min Act: -0.1700
Data Index: 1037033 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9484. Min Range: -6.9484
Max Act: 6.2921. Min Act: -0.1700
Data Index: 4831346 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9484. Min Range: -6.9484
Max Act: 6.2609. Min Act: -0.1700
Data Index: 6928672 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9484. Min Range: -6.9484
Max Act: 6.2296. Min Act: -0.1700
Data Index: 6207468 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9484. Min Range: -6.9484
Max Act: 6.1984. Min Act: -0.1700
Data Index: 6439670 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9484. Min Range: -6.9484
Max Act: 6.2296. Min Act: -0.1700
Data Index: 6947127 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9484. Min Range: -6.9484
Max Act: 6.1984. Min Act: -0.1700
Data Index: 4483750 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9484. Min Range: -6.9484
Max Act: 6.1984. Min Act: -0.1700
Data Index: 2898099 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9484. Min Range: -6.9484
Max Act: 6.1671. Min Act: -0.1700
Data Index: 1809078 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9484. Min Range: -6.9484
Max Act: 6.1671. Min Act: -0.1700
Data Index: 1702962 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9484. Min Range: -6.9484
Max Act: 6.1671. Min Act: -0.1700
Data Index: 7592912 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9484. Min Range: -6.9484
Max Act: 6.1671. Min Act: -0.1700
Data Index: 4769608 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9484. Min Range: -6.9484
Max Act: 6.1359. Min Act: -0.1700
Data Index: 917551 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #19