Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1455 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.9258. Min Range: -3.9258
Max Act: 3.9258. Min Act: -0.1700
Data Index: 2761747 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9258. Min Range: -3.9258
Max Act: 3.7694. Min Act: -0.1700
Data Index: 1191488 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9258. Min Range: -3.9258
Max Act: 3.6756. Min Act: -0.1700
Data Index: 1901497 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9258. Min Range: -3.9258
Max Act: 3.6600. Min Act: -0.1700
Data Index: 7213075 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9258. Min Range: -3.9258
Max Act: 3.6756. Min Act: -0.1700
Data Index: 5752252 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9258. Min Range: -3.9258
Max Act: 3.6756. Min Act: -0.1700
Data Index: 6314110 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9258. Min Range: -3.9258
Max Act: 3.6600. Min Act: -0.1700
Data Index: 831966 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9258. Min Range: -3.9258
Max Act: 3.6443. Min Act: -0.1700
Data Index: 5667284 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9258. Min Range: -3.9258
Max Act: 3.6443. Min Act: -0.1700
Data Index: 6816867 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9258. Min Range: -3.9258
Max Act: 3.6287. Min Act: -0.1700
Data Index: 7442685 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9258. Min Range: -3.9258
Max Act: 3.6443. Min Act: -0.1700
Data Index: 2596263 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9258. Min Range: -3.9258
Max Act: 3.5974. Min Act: -0.1700
Data Index: 3194268 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9258. Min Range: -3.9258
Max Act: 3.6130. Min Act: -0.1700
Data Index: 5455723 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9258. Min Range: -3.9258
Max Act: 3.6130. Min Act: -0.1700
Data Index: 2906443 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9258. Min Range: -3.9258
Max Act: 3.6287. Min Act: -0.1700
Data Index: 868924 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9258. Min Range: -3.9258
Max Act: 3.5974. Min Act: -0.1700
Data Index: 4881281 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9258. Min Range: -3.9258
Max Act: 3.6130. Min Act: -0.1700
Data Index: 5679563 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9258. Min Range: -3.9258
Max Act: 3.5974. Min Act: -0.1700
Data Index: 6532161 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9258. Min Range: -3.9258
Max Act: 3.6287. Min Act: -0.1700
Data Index: 7453073 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9258. Min Range: -3.9258
Max Act: 3.6130. Min Act: -0.1700
Data Index: 7435445 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #19