Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 539 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4295. Min Range: -6.4295
Max Act: 6.4295. Min Act: -0.1700
Data Index: 8215902 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4295. Min Range: -6.4295
Max Act: 6.0233. Min Act: -0.1700
Data Index: 387161 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4295. Min Range: -6.4295
Max Act: 5.9295. Min Act: -0.1700
Data Index: 8634509 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4295. Min Range: -6.4295
Max Act: 5.9295. Min Act: -0.1700
Data Index: 6436935 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4295. Min Range: -6.4295
Max Act: 5.9295. Min Act: -0.1700
Data Index: 5213241 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4295. Min Range: -6.4295
Max Act: 5.9295. Min Act: -0.1700
Data Index: 5962880 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4295. Min Range: -6.4295
Max Act: 5.8983. Min Act: -0.1700
Data Index: 3386506 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4295. Min Range: -6.4295
Max Act: 5.8983. Min Act: -0.1700
Data Index: 7090727 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4295. Min Range: -6.4295
Max Act: 5.8670. Min Act: -0.1700
Data Index: 1524244 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4295. Min Range: -6.4295
Max Act: 5.8670. Min Act: -0.1700
Data Index: 606261 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4295. Min Range: -6.4295
Max Act: 5.8670. Min Act: -0.1700
Data Index: 7552119 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4295. Min Range: -6.4295
Max Act: 5.8358. Min Act: -0.1700
Data Index: 7004496 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4295. Min Range: -6.4295
Max Act: 5.8045. Min Act: -0.1700
Data Index: 4804787 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4295. Min Range: -6.4295
Max Act: 5.8045. Min Act: -0.1700
Data Index: 414991 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4295. Min Range: -6.4295
Max Act: 5.7733. Min Act: -0.1700
Data Index: 4733257 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4295. Min Range: -6.4295
Max Act: 5.7733. Min Act: -0.1700
Data Index: 4083097 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4295. Min Range: -6.4295
Max Act: 5.7420. Min Act: -0.1700
Data Index: 8430092 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4295. Min Range: -6.4295
Max Act: 5.7420. Min Act: -0.1700
Data Index: 5964841 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4295. Min Range: -6.4295
Max Act: 5.7733. Min Act: -0.1700
Data Index: 4942866 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4295. Min Range: -6.4295
Max Act: 5.7108. Min Act: -0.1700
Data Index: 5193841 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #19