Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 424 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.1273. Min Range: -2.1273
Max Act: 2.1273. Min Act: -0.1700
Data Index: 5577659 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.1273. Min Range: -2.1273
Max Act: 2.1105. Min Act: -0.1700
Data Index: 2528960 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.1273. Min Range: -2.1273
Max Act: 2.1105. Min Act: -0.1700
Data Index: 3688790 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.1273. Min Range: -2.1273
Max Act: 2.0938. Min Act: -0.1700
Data Index: 3551348 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.1273. Min Range: -2.1273
Max Act: 2.0602. Min Act: -0.1700
Data Index: 316759 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.1273. Min Range: -2.1273
Max Act: 2.0770. Min Act: -0.1700
Data Index: 8405669 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.1273. Min Range: -2.1273
Max Act: 2.0266. Min Act: -0.1700
Data Index: 2024505 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.1273. Min Range: -2.1273
Max Act: 2.0266. Min Act: -0.1700
Data Index: 4458409 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.1273. Min Range: -2.1273
Max Act: 2.0097. Min Act: -0.1700
Data Index: 3153368 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.1273. Min Range: -2.1273
Max Act: 1.9928. Min Act: -0.1700
Data Index: 5208200 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.1273. Min Range: -2.1273
Max Act: 1.9928. Min Act: -0.1700
Data Index: 6919392 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.1273. Min Range: -2.1273
Max Act: 1.9928. Min Act: -0.1700
Data Index: 1450099 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.1273. Min Range: -2.1273
Max Act: 1.9928. Min Act: -0.1700
Data Index: 2282618 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.1273. Min Range: -2.1273
Max Act: 1.9928. Min Act: -0.1700
Data Index: 7985615 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.1273. Min Range: -2.1273
Max Act: 1.9759. Min Act: -0.1700
Data Index: 4458408 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.1273. Min Range: -2.1273
Max Act: 1.9759. Min Act: -0.1700
Data Index: 2622161 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.1273. Min Range: -2.1273
Max Act: 1.9759. Min Act: -0.1700
Data Index: 7257673 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.1273. Min Range: -2.1273
Max Act: 1.9589. Min Act: -0.1700
Data Index: 1215890 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.1273. Min Range: -2.1273
Max Act: 1.9759. Min Act: -0.1700
Data Index: 5020882 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.1273. Min Range: -2.1273
Max Act: 1.9759. Min Act: -0.1700
Data Index: 8680252 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #19