Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 4037 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.3145. Min Range: -2.3145
Max Act: 2.3145. Min Act: -0.1700
Data Index: 7271493 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3145. Min Range: -2.3145
Max Act: 2.2981. Min Act: -0.1700
Data Index: 4173898 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3145. Min Range: -2.3145
Max Act: 2.2651. Min Act: -0.1700
Data Index: 1234466 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3145. Min Range: -2.3145
Max Act: 2.2486. Min Act: -0.1700
Data Index: 4813739 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3145. Min Range: -2.3145
Max Act: 2.2486. Min Act: -0.1700
Data Index: 2772209 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3145. Min Range: -2.3145
Max Act: 2.2321. Min Act: -0.1700
Data Index: 4023355 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3145. Min Range: -2.3145
Max Act: 2.2321. Min Act: -0.1700
Data Index: 5638144 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3145. Min Range: -2.3145
Max Act: 2.2321. Min Act: -0.1700
Data Index: 3232622 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3145. Min Range: -2.3145
Max Act: 2.2155. Min Act: -0.1700
Data Index: 5568925 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3145. Min Range: -2.3145
Max Act: 2.2155. Min Act: -0.1700
Data Index: 2677741 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3145. Min Range: -2.3145
Max Act: 2.1989. Min Act: -0.1700
Data Index: 786280 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3145. Min Range: -2.3145
Max Act: 2.2155. Min Act: -0.1700
Data Index: 5604734 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3145. Min Range: -2.3145
Max Act: 2.2155. Min Act: -0.1700
Data Index: 2403541 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3145. Min Range: -2.3145
Max Act: 2.2321. Min Act: -0.1700
Data Index: 7294606 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3145. Min Range: -2.3145
Max Act: 2.2155. Min Act: -0.1700
Data Index: 1579044 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3145. Min Range: -2.3145
Max Act: 2.2155. Min Act: -0.1700
Data Index: 3389013 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3145. Min Range: -2.3145
Max Act: 2.1989. Min Act: -0.1700
Data Index: 1123262 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3145. Min Range: -2.3145
Max Act: 2.1989. Min Act: -0.1700
Data Index: 5623789 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3145. Min Range: -2.3145
Max Act: 2.1823. Min Act: -0.1700
Data Index: 3304039 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3145. Min Range: -2.3145
Max Act: 2.1823. Min Act: -0.1700
Data Index: 3103216 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19