Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6183 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5379. Min Range: -6.5379
Max Act: 6.5379. Min Act: -0.1700
Data Index: 8401142 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5379. Min Range: -6.5379
Max Act: 6.4442. Min Act: -0.1700
Data Index: 5702498 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5379. Min Range: -6.5379
Max Act: 6.4442. Min Act: -0.1700
Data Index: 4067891 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5379. Min Range: -6.5379
Max Act: 6.3817. Min Act: -0.1700
Data Index: 947307 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5379. Min Range: -6.5379
Max Act: 6.2567. Min Act: -0.1700
Data Index: 33301 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5379. Min Range: -6.5379
Max Act: 6.2879. Min Act: -0.1700
Data Index: 41640 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5379. Min Range: -6.5379
Max Act: 6.2879. Min Act: -0.1700
Data Index: 5168812 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5379. Min Range: -6.5379
Max Act: 6.2567. Min Act: -0.1700
Data Index: 4351511 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5379. Min Range: -6.5379
Max Act: 6.2254. Min Act: -0.1700
Data Index: 4911789 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5379. Min Range: -6.5379
Max Act: 6.2567. Min Act: -0.1700
Data Index: 7408284 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5379. Min Range: -6.5379
Max Act: 6.1942. Min Act: -0.1700
Data Index: 6124913 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5379. Min Range: -6.5379
Max Act: 6.1629. Min Act: -0.1700
Data Index: 1315187 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5379. Min Range: -6.5379
Max Act: 6.1317. Min Act: -0.1700
Data Index: 995620 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5379. Min Range: -6.5379
Max Act: 6.1317. Min Act: -0.1700
Data Index: 1261142 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5379. Min Range: -6.5379
Max Act: 6.1629. Min Act: -0.1700
Data Index: 6341259 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5379. Min Range: -6.5379
Max Act: 6.1004. Min Act: -0.1700
Data Index: 8186278 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5379. Min Range: -6.5379
Max Act: 6.1004. Min Act: -0.1700
Data Index: 6693035 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5379. Min Range: -6.5379
Max Act: 6.1004. Min Act: -0.1700
Data Index: 6627910 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5379. Min Range: -6.5379
Max Act: 6.1004. Min Act: -0.1700
Data Index: 2386341 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5379. Min Range: -6.5379
Max Act: 6.1004. Min Act: -0.1700
Data Index: 7532990 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19