Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3915 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5983. Min Range: -6.5983
Max Act: 6.5983. Min Act: -0.1700
Data Index: 6445723 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5983. Min Range: -6.5983
Max Act: 6.5358. Min Act: -0.1699
Data Index: 7144889 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5983. Min Range: -6.5983
Max Act: 6.5046. Min Act: -0.1700
Data Index: 8780285 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5983. Min Range: -6.5983
Max Act: 6.5046. Min Act: -0.1700
Data Index: 359282 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5983. Min Range: -6.5983
Max Act: 6.4733. Min Act: -0.1700
Data Index: 147469 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5983. Min Range: -6.5983
Max Act: 6.4733. Min Act: -0.1700
Data Index: 5216521 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5983. Min Range: -6.5983
Max Act: 6.4421. Min Act: -0.1700
Data Index: 1779832 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5983. Min Range: -6.5983
Max Act: 6.4733. Min Act: -0.1700
Data Index: 129431 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5983. Min Range: -6.5983
Max Act: 6.4733. Min Act: -0.1700
Data Index: 6546511 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5983. Min Range: -6.5983
Max Act: 6.4421. Min Act: -0.1700
Data Index: 6557711 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5983. Min Range: -6.5983
Max Act: 6.3796. Min Act: -0.1700
Data Index: 3603208 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5983. Min Range: -6.5983
Max Act: 6.3171. Min Act: -0.1700
Data Index: 3012082 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5983. Min Range: -6.5983
Max Act: 6.2858. Min Act: -0.1700
Data Index: 4279623 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5983. Min Range: -6.5983
Max Act: 6.2858. Min Act: -0.1698
Data Index: 7572724 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5983. Min Range: -6.5983
Max Act: 6.2546. Min Act: -0.1700
Data Index: 92930 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5983. Min Range: -6.5983
Max Act: 6.2546. Min Act: -0.1700
Data Index: 7054159 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5983. Min Range: -6.5983
Max Act: 6.2546. Min Act: -0.1700
Data Index: 890417 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5983. Min Range: -6.5983
Max Act: 6.2233. Min Act: -0.1700
Data Index: 4237399 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5983. Min Range: -6.5983
Max Act: 6.2546. Min Act: -0.1700
Data Index: 2846760 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5983. Min Range: -6.5983
Max Act: 6.2546. Min Act: -0.1700
Data Index: 3539943 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #19