Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2747 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3216. Min Range: -6.3216
Max Act: 6.3216. Min Act: -0.1700
Data Index: 7661188 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3216. Min Range: -6.3216
Max Act: 6.1966. Min Act: -0.1700
Data Index: 2843175 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3216. Min Range: -6.3216
Max Act: 6.0404. Min Act: -0.1700
Data Index: 4140563 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3216. Min Range: -6.3216
Max Act: 6.0091. Min Act: -0.1700
Data Index: 7254688 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3216. Min Range: -6.3216
Max Act: 5.9779. Min Act: -0.1700
Data Index: 576688 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3216. Min Range: -6.3216
Max Act: 5.9154. Min Act: -0.1700
Data Index: 3201854 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3216. Min Range: -6.3216
Max Act: 5.9154. Min Act: -0.1700
Data Index: 1390815 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3216. Min Range: -6.3216
Max Act: 5.8841. Min Act: -0.1700
Data Index: 5049232 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3216. Min Range: -6.3216
Max Act: 5.8841. Min Act: -0.1700
Data Index: 5685035 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3216. Min Range: -6.3216
Max Act: 5.8529. Min Act: -0.1700
Data Index: 2045618 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3216. Min Range: -6.3216
Max Act: 5.8841. Min Act: -0.1700
Data Index: 5952464 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3216. Min Range: -6.3216
Max Act: 5.8529. Min Act: -0.1700
Data Index: 3348194 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3216. Min Range: -6.3216
Max Act: 5.8529. Min Act: -0.1700
Data Index: 6877876 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3216. Min Range: -6.3216
Max Act: 5.8529. Min Act: -0.1700
Data Index: 2124617 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3216. Min Range: -6.3216
Max Act: 5.8216. Min Act: -0.1700
Data Index: 2329516 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3216. Min Range: -6.3216
Max Act: 5.8216. Min Act: -0.1700
Data Index: 4843888 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3216. Min Range: -6.3216
Max Act: 5.8216. Min Act: -0.1700
Data Index: 4902409 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3216. Min Range: -6.3216
Max Act: 5.7904. Min Act: -0.1700
Data Index: 1382833 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3216. Min Range: -6.3216
Max Act: 5.7904. Min Act: -0.1700
Data Index: 1987821 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3216. Min Range: -6.3216
Max Act: 5.7904. Min Act: -0.1700
Data Index: 1388049 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #19