Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2576 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.2506. Min Range: -6.2506
Max Act: 6.2506. Min Act: -0.1700
Data Index: 1466234 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2506. Min Range: -6.2506
Max Act: 6.0006. Min Act: -0.1700
Data Index: 1466243 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2506. Min Range: -6.2506
Max Act: 6.0006. Min Act: -0.1700
Data Index: 1466232 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2506. Min Range: -6.2506
Max Act: 5.8756. Min Act: -0.1700
Data Index: 4972091 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2506. Min Range: -6.2506
Max Act: 5.8443. Min Act: -0.1700
Data Index: 5137224 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2506. Min Range: -6.2506
Max Act: 5.8443. Min Act: -0.1700
Data Index: 4483370 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2506. Min Range: -6.2506
Max Act: 5.8131. Min Act: -0.1700
Data Index: 2636633 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2506. Min Range: -6.2506
Max Act: 5.7818. Min Act: -0.1700
Data Index: 1466236 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2506. Min Range: -6.2506
Max Act: 5.7506. Min Act: -0.1700
Data Index: 860393 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2506. Min Range: -6.2506
Max Act: 5.7193. Min Act: -0.1700
Data Index: 4483365 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2506. Min Range: -6.2506
Max Act: 5.6881. Min Act: -0.1700
Data Index: 860390 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2506. Min Range: -6.2506
Max Act: 5.6881. Min Act: -0.1700
Data Index: 7435987 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2506. Min Range: -6.2506
Max Act: 5.6881. Min Act: -0.1700
Data Index: 5087878 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2506. Min Range: -6.2506
Max Act: 5.6881. Min Act: -0.1700
Data Index: 6087252 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2506. Min Range: -6.2506
Max Act: 5.6568. Min Act: -0.1700
Data Index: 6087244 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2506. Min Range: -6.2506
Max Act: 5.6568. Min Act: -0.1700
Data Index: 860378 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2506. Min Range: -6.2506
Max Act: 5.6568. Min Act: -0.1700
Data Index: 5087870 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2506. Min Range: -6.2506
Max Act: 5.6256. Min Act: -0.1700
Data Index: 4879449 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2506. Min Range: -6.2506
Max Act: 5.6568. Min Act: -0.1700
Data Index: 5137218 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2506. Min Range: -6.2506
Max Act: 5.6256. Min Act: -0.1700
Data Index: 5137213 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19