Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4080 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4277. Min Range: -6.4277
Max Act: 6.4277. Min Act: -0.1700
Data Index: 3880206 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4277. Min Range: -6.4277
Max Act: 5.9277. Min Act: -0.1700
Data Index: 7226808 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4277. Min Range: -6.4277
Max Act: 5.8965. Min Act: -0.1700
Data Index: 4051797 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4277. Min Range: -6.4277
Max Act: 5.8340. Min Act: -0.1700
Data Index: 5749783 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4277. Min Range: -6.4277
Max Act: 5.8652. Min Act: -0.1700
Data Index: 2680123 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4277. Min Range: -6.4277
Max Act: 5.8340. Min Act: -0.1700
Data Index: 7463565 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4277. Min Range: -6.4277
Max Act: 5.6465. Min Act: -0.1700
Data Index: 5348083 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4277. Min Range: -6.4277
Max Act: 5.6465. Min Act: -0.1700
Data Index: 2627847 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4277. Min Range: -6.4277
Max Act: 5.6465. Min Act: -0.1700
Data Index: 5995273 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4277. Min Range: -6.4277
Max Act: 5.5527. Min Act: -0.1700
Data Index: 16201 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4277. Min Range: -6.4277
Max Act: 5.5527. Min Act: -0.1700
Data Index: 7201148 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4277. Min Range: -6.4277
Max Act: 5.5840. Min Act: -0.1700
Data Index: 1184132 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4277. Min Range: -6.4277
Max Act: 5.5527. Min Act: -0.1700
Data Index: 5127084 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4277. Min Range: -6.4277
Max Act: 5.5527. Min Act: -0.1700
Data Index: 1959754 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4277. Min Range: -6.4277
Max Act: 5.5215. Min Act: -0.1700
Data Index: 7466623 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4277. Min Range: -6.4277
Max Act: 5.5527. Min Act: -0.1700
Data Index: 8781398 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4277. Min Range: -6.4277
Max Act: 5.5215. Min Act: -0.1700
Data Index: 3504388 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4277. Min Range: -6.4277
Max Act: 5.5215. Min Act: -0.1700
Data Index: 4211686 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4277. Min Range: -6.4277
Max Act: 5.5215. Min Act: -0.1700
Data Index: 1273640 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4277. Min Range: -6.4277
Max Act: 5.5215. Min Act: -0.1700
Data Index: 2781020 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #19