Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3979 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.8369. Min Range: -2.8369
Max Act: 2.8369. Min Act: -0.1700
Data Index: 3290525 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8369. Min Range: -2.8369
Max Act: 2.6773. Min Act: -0.1700
Data Index: 6170892 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8369. Min Range: -2.8369
Max Act: 2.6613. Min Act: -0.1700
Data Index: 7553096 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8369. Min Range: -2.8369
Max Act: 2.6453. Min Act: -0.1700
Data Index: 2277235 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8369. Min Range: -2.8369
Max Act: 2.6453. Min Act: -0.1700
Data Index: 8725098 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8369. Min Range: -2.8369
Max Act: 2.6292. Min Act: -0.1700
Data Index: 2663307 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8369. Min Range: -2.8369
Max Act: 2.6131. Min Act: -0.1700
Data Index: 3187028 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8369. Min Range: -2.8369
Max Act: 2.6131. Min Act: -0.1700
Data Index: 478240 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8369. Min Range: -2.8369
Max Act: 2.6131. Min Act: -0.1700
Data Index: 237135 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8369. Min Range: -2.8369
Max Act: 2.6131. Min Act: -0.1700
Data Index: 206567 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8369. Min Range: -2.8369
Max Act: 2.5970. Min Act: -0.1700
Data Index: 1927378 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8369. Min Range: -2.8369
Max Act: 2.5970. Min Act: -0.1700
Data Index: 6520725 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8369. Min Range: -2.8369
Max Act: 2.5970. Min Act: -0.1700
Data Index: 5483171 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8369. Min Range: -2.8369
Max Act: 2.5970. Min Act: -0.1700
Data Index: 5675625 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8369. Min Range: -2.8369
Max Act: 2.5970. Min Act: -0.1700
Data Index: 6577919 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8369. Min Range: -2.8369
Max Act: 2.5970. Min Act: -0.1700
Data Index: 2720487 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8369. Min Range: -2.8369
Max Act: 2.5809. Min Act: -0.1700
Data Index: 2161916 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8369. Min Range: -2.8369
Max Act: 2.5970. Min Act: -0.1700
Data Index: 5030268 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8369. Min Range: -2.8369
Max Act: 2.5970. Min Act: -0.1700
Data Index: 6270117 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8369. Min Range: -2.8369
Max Act: 2.5970. Min Act: -0.1700
Data Index: 7279980 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #19