Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3260 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9179. Min Range: -3.9179
Max Act: 3.9179. Min Act: -0.1700
Data Index: 2976895 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9179. Min Range: -3.9179
Max Act: 3.9179. Min Act: -0.1700
Data Index: 6275479 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9179. Min Range: -3.9179
Max Act: 3.9179. Min Act: -0.1700
Data Index: 6076047 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9179. Min Range: -3.9179
Max Act: 3.9179. Min Act: -0.1700
Data Index: 6720325 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9179. Min Range: -3.9179
Max Act: 3.8867. Min Act: -0.1700
Data Index: 330740 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9179. Min Range: -3.9179
Max Act: 3.8554. Min Act: -0.1700
Data Index: 2346748 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9179. Min Range: -3.9179
Max Act: 3.8554. Min Act: -0.1700
Data Index: 4467547 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9179. Min Range: -3.9179
Max Act: 3.8554. Min Act: -0.1700
Data Index: 6250544 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9179. Min Range: -3.9179
Max Act: 3.8554. Min Act: -0.1700
Data Index: 6668400 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9179. Min Range: -3.9179
Max Act: 3.8241. Min Act: -0.1700
Data Index: 3080224 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9179. Min Range: -3.9179
Max Act: 3.8241. Min Act: -0.1700
Data Index: 2552662 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9179. Min Range: -3.9179
Max Act: 3.8241. Min Act: -0.1700
Data Index: 6701658 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9179. Min Range: -3.9179
Max Act: 3.7928. Min Act: -0.1700
Data Index: 3380712 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9179. Min Range: -3.9179
Max Act: 3.8241. Min Act: -0.1700
Data Index: 4964746 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9179. Min Range: -3.9179
Max Act: 3.8241. Min Act: -0.1700
Data Index: 1440617 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9179. Min Range: -3.9179
Max Act: 3.8241. Min Act: -0.1700
Data Index: 1352385 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9179. Min Range: -3.9179
Max Act: 3.7928. Min Act: -0.1700
Data Index: 4201758 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9179. Min Range: -3.9179
Max Act: 3.7928. Min Act: -0.1700
Data Index: 321880 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9179. Min Range: -3.9179
Max Act: 3.8241. Min Act: -0.1700
Data Index: 184934 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9179. Min Range: -3.9179
Max Act: 3.7928. Min Act: -0.1700
Data Index: 2651330 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #19