Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1320 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.1041. Min Range: -1.1041
Max Act: 1.1041. Min Act: -0.1700
Data Index: 7757660 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1041. Min Range: -1.1041
Max Act: 1.0516. Min Act: -0.1700
Data Index: 294032 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1041. Min Range: -1.1041
Max Act: 1.0168. Min Act: -0.1700
Data Index: 1703620 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1041. Min Range: -1.1041
Max Act: 0.9821. Min Act: -0.1700
Data Index: 573462 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1041. Min Range: -1.1041
Max Act: 0.9821. Min Act: -0.1700
Data Index: 4054651 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1041. Min Range: -1.1041
Max Act: 0.9821. Min Act: -0.1700
Data Index: 2283185 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1041. Min Range: -1.1041
Max Act: 0.9994. Min Act: -0.1700
Data Index: 7254909 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1041. Min Range: -1.1041
Max Act: 0.9821. Min Act: -0.1700
Data Index: 2838009 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1041. Min Range: -1.1041
Max Act: 0.9475. Min Act: -0.1700
Data Index: 4057999 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1041. Min Range: -1.1041
Max Act: 0.9821. Min Act: -0.1700
Data Index: 7816843 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1041. Min Range: -1.1041
Max Act: 0.9821. Min Act: -0.1699
Data Index: 5657944 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1041. Min Range: -1.1041
Max Act: 0.9475. Min Act: -0.1700
Data Index: 1462319 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1041. Min Range: -1.1041
Max Act: 0.9648. Min Act: -0.1700
Data Index: 1941053 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1041. Min Range: -1.1041
Max Act: 0.9475. Min Act: -0.1700
Data Index: 1644775 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1041. Min Range: -1.1041
Max Act: 0.9475. Min Act: -0.1700
Data Index: 5766215 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1041. Min Range: -1.1041
Max Act: 0.9648. Min Act: -0.1700
Data Index: 6673621 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1041. Min Range: -1.1041
Max Act: 0.9303. Min Act: -0.1700
Data Index: 500031 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1041. Min Range: -1.1041
Max Act: 0.9303. Min Act: -0.1700
Data Index: 899993 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1041. Min Range: -1.1041
Max Act: 0.9303. Min Act: -0.1700
Data Index: 2731402 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1041. Min Range: -1.1041
Max Act: 0.9475. Min Act: -0.1700
Data Index: 507991 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #19