Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1377 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.2924. Min Range: -7.2924
Max Act: 7.2924. Min Act: -0.1700
Data Index: 6438277 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2924. Min Range: -7.2924
Max Act: 7.0736. Min Act: -0.1699
Data Index: 2829115 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2924. Min Range: -7.2924
Max Act: 7.0111. Min Act: -0.1700
Data Index: 8625701 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2924. Min Range: -7.2924
Max Act: 6.9486. Min Act: -0.1700
Data Index: 5936674 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2924. Min Range: -7.2924
Max Act: 6.9174. Min Act: -0.1700
Data Index: 1094299 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2924. Min Range: -7.2924
Max Act: 6.7924. Min Act: -0.1692
Data Index: 4906935 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2924. Min Range: -7.2924
Max Act: 6.7924. Min Act: -0.1700
Data Index: 3596059 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2924. Min Range: -7.2924
Max Act: 6.6986. Min Act: -0.1700
Data Index: 804529 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2924. Min Range: -7.2924
Max Act: 6.7299. Min Act: -0.1700
Data Index: 1234598 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2924. Min Range: -7.2924
Max Act: 6.6986. Min Act: -0.1700
Data Index: 744211 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2924. Min Range: -7.2924
Max Act: 6.6361. Min Act: -0.1700
Data Index: 193342 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2924. Min Range: -7.2924
Max Act: 6.6674. Min Act: -0.1700
Data Index: 6877177 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2924. Min Range: -7.2924
Max Act: 6.6049. Min Act: -0.1700
Data Index: 3276815 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2924. Min Range: -7.2924
Max Act: 6.5736. Min Act: -0.1700
Data Index: 4358633 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2924. Min Range: -7.2924
Max Act: 6.5736. Min Act: -0.1700
Data Index: 2432443 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2924. Min Range: -7.2924
Max Act: 6.5736. Min Act: -0.1700
Data Index: 8729205 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2924. Min Range: -7.2924
Max Act: 6.5736. Min Act: -0.1700
Data Index: 5578155 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2924. Min Range: -7.2924
Max Act: 6.5736. Min Act: -0.1699
Data Index: 3033085 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2924. Min Range: -7.2924
Max Act: 6.5736. Min Act: -0.1700
Data Index: 190210 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2924. Min Range: -7.2924
Max Act: 6.5736. Min Act: -0.1700
Data Index: 3323652 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #19