Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1998 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.5266. Min Range: -5.5266
Max Act: 5.5266. Min Act: -0.1700
Data Index: 4312474 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5266. Min Range: -5.5266
Max Act: 5.4329. Min Act: -0.1700
Data Index: 116100 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5266. Min Range: -5.5266
Max Act: 5.4016. Min Act: -0.1700
Data Index: 2165996 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5266. Min Range: -5.5266
Max Act: 5.4016. Min Act: -0.1700
Data Index: 7353396 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5266. Min Range: -5.5266
Max Act: 5.3704. Min Act: -0.1700
Data Index: 1963105 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5266. Min Range: -5.5266
Max Act: 5.3391. Min Act: -0.1700
Data Index: 620342 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5266. Min Range: -5.5266
Max Act: 5.3391. Min Act: -0.1700
Data Index: 6093938 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5266. Min Range: -5.5266
Max Act: 5.3704. Min Act: -0.1700
Data Index: 2705059 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5266. Min Range: -5.5266
Max Act: 5.3391. Min Act: -0.1700
Data Index: 6462566 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5266. Min Range: -5.5266
Max Act: 5.3079. Min Act: -0.1700
Data Index: 4062845 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5266. Min Range: -5.5266
Max Act: 5.2766. Min Act: -0.1700
Data Index: 3935219 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5266. Min Range: -5.5266
Max Act: 5.2766. Min Act: -0.1700
Data Index: 1104795 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5266. Min Range: -5.5266
Max Act: 5.2454. Min Act: -0.1700
Data Index: 985426 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5266. Min Range: -5.5266
Max Act: 5.2454. Min Act: -0.1700
Data Index: 6885438 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5266. Min Range: -5.5266
Max Act: 5.2141. Min Act: -0.1700
Data Index: 8337300 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5266. Min Range: -5.5266
Max Act: 5.2454. Min Act: -0.1700
Data Index: 6438244 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5266. Min Range: -5.5266
Max Act: 5.2141. Min Act: -0.1700
Data Index: 5583430 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5266. Min Range: -5.5266
Max Act: 5.2454. Min Act: -0.1700
Data Index: 7874873 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5266. Min Range: -5.5266
Max Act: 5.2141. Min Act: -0.1700
Data Index: 3330808 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5266. Min Range: -5.5266
Max Act: 5.2141. Min Act: -0.1700
Data Index: 3492075 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #19