Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3295 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.4133. Min Range: -4.4133
Max Act: 4.4133. Min Act: -0.1700
Data Index: 5249007 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4133. Min Range: -4.4133
Max Act: 4.4133. Min Act: -0.1700
Data Index: 6006034 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4133. Min Range: -4.4133
Max Act: 4.3821. Min Act: -0.1700
Data Index: 2264123 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4133. Min Range: -4.4133
Max Act: 4.3821. Min Act: -0.1700
Data Index: 4351253 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4133. Min Range: -4.4133
Max Act: 4.3508. Min Act: -0.1700
Data Index: 5674579 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4133. Min Range: -4.4133
Max Act: 4.3196. Min Act: -0.1700
Data Index: 4441429 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4133. Min Range: -4.4133
Max Act: 4.3196. Min Act: -0.1700
Data Index: 2237890 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4133. Min Range: -4.4133
Max Act: 4.3196. Min Act: -0.1700
Data Index: 640646 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4133. Min Range: -4.4133
Max Act: 4.3196. Min Act: -0.1700
Data Index: 6172499 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4133. Min Range: -4.4133
Max Act: 4.3196. Min Act: -0.1700
Data Index: 8665479 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4133. Min Range: -4.4133
Max Act: 4.2258. Min Act: -0.1700
Data Index: 5138129 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4133. Min Range: -4.4133
Max Act: 4.2258. Min Act: -0.1700
Data Index: 719707 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4133. Min Range: -4.4133
Max Act: 4.2258. Min Act: -0.1700
Data Index: 6781175 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4133. Min Range: -4.4133
Max Act: 4.1946. Min Act: -0.1700
Data Index: 3788794 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4133. Min Range: -4.4133
Max Act: 4.2258. Min Act: -0.1700
Data Index: 6184730 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4133. Min Range: -4.4133
Max Act: 4.2258. Min Act: -0.1700
Data Index: 894214 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4133. Min Range: -4.4133
Max Act: 4.2258. Min Act: -0.1700
Data Index: 5827944 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4133. Min Range: -4.4133
Max Act: 4.2258. Min Act: -0.1700
Data Index: 2958444 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4133. Min Range: -4.4133
Max Act: 4.2258. Min Act: -0.1700
Data Index: 5602457 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4133. Min Range: -4.4133
Max Act: 4.2258. Min Act: -0.1699
Data Index: 2483733 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #19