Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2677 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 9.9489. Min Range: -9.9489
Max Act: 9.9489. Min Act: -0.1700
Data Index: 6087541 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9489. Min Range: -9.9489
Max Act: 9.4489. Min Act: -0.1700
Data Index: 582721 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9489. Min Range: -9.9489
Max Act: 9.2614. Min Act: -0.1700
Data Index: 7719892 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9489. Min Range: -9.9489
Max Act: 9.1364. Min Act: -0.1700
Data Index: 5738506 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9489. Min Range: -9.9489
Max Act: 9.1989. Min Act: -0.1700
Data Index: 166624 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9489. Min Range: -9.9489
Max Act: 9.1989. Min Act: -0.1700
Data Index: 3487425 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9489. Min Range: -9.9489
Max Act: 9.1364. Min Act: -0.1700
Data Index: 2854276 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9489. Min Range: -9.9489
Max Act: 9.1364. Min Act: -0.1700
Data Index: 7206689 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9489. Min Range: -9.9489
Max Act: 9.1364. Min Act: -0.1700
Data Index: 7093501 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9489. Min Range: -9.9489
Max Act: 9.1364. Min Act: -0.1700
Data Index: 4577169 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9489. Min Range: -9.9489
Max Act: 9.1364. Min Act: -0.1700
Data Index: 1258424 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9489. Min Range: -9.9489
Max Act: 9.1364. Min Act: -0.1700
Data Index: 718866 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9489. Min Range: -9.9489
Max Act: 9.0739. Min Act: -0.1700
Data Index: 6963115 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9489. Min Range: -9.9489
Max Act: 9.0739. Min Act: -0.1700
Data Index: 3458019 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9489. Min Range: -9.9489
Max Act: 9.0739. Min Act: -0.1700
Data Index: 6712240 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9489. Min Range: -9.9489
Max Act: 9.0739. Min Act: -0.1700
Data Index: 4354174 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9489. Min Range: -9.9489
Max Act: 9.0739. Min Act: -0.1700
Data Index: 4165568 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9489. Min Range: -9.9489
Max Act: 9.0739. Min Act: -0.1700
Data Index: 3586764 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9489. Min Range: -9.9489
Max Act: 9.0739. Min Act: -0.1700
Data Index: 5483641 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9489. Min Range: -9.9489
Max Act: 9.0739. Min Act: -0.1700
Data Index: 1526315 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #19