Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1774 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5712. Min Range: -5.5712
Max Act: 5.5712. Min Act: -0.1700
Data Index: 2948713 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5712. Min Range: -5.5712
Max Act: 5.5399. Min Act: -0.1700
Data Index: 6765114 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5712. Min Range: -5.5712
Max Act: 5.4149. Min Act: -0.1700
Data Index: 1933452 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5712. Min Range: -5.5712
Max Act: 5.4774. Min Act: -0.1700
Data Index: 684911 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5712. Min Range: -5.5712
Max Act: 5.4774. Min Act: -0.1700
Data Index: 744100 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5712. Min Range: -5.5712
Max Act: 5.4149. Min Act: -0.1700
Data Index: 57069 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5712. Min Range: -5.5712
Max Act: 5.4149. Min Act: -0.1700
Data Index: 8627738 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5712. Min Range: -5.5712
Max Act: 5.4149. Min Act: -0.1700
Data Index: 4818128 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5712. Min Range: -5.5712
Max Act: 5.4462. Min Act: -0.1700
Data Index: 2657846 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5712. Min Range: -5.5712
Max Act: 5.4149. Min Act: -0.1700
Data Index: 6179266 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5712. Min Range: -5.5712
Max Act: 5.3837. Min Act: -0.1700
Data Index: 2596098 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5712. Min Range: -5.5712
Max Act: 5.3837. Min Act: -0.1700
Data Index: 44247 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5712. Min Range: -5.5712
Max Act: 5.3837. Min Act: -0.1700
Data Index: 1758068 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5712. Min Range: -5.5712
Max Act: 5.3837. Min Act: -0.1700
Data Index: 5253782 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5712. Min Range: -5.5712
Max Act: 5.3837. Min Act: -0.1700
Data Index: 669185 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5712. Min Range: -5.5712
Max Act: 5.4149. Min Act: -0.1700
Data Index: 2592197 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5712. Min Range: -5.5712
Max Act: 5.3524. Min Act: -0.1700
Data Index: 4488836 (Open Web Text)
Max Activating Token Index: 151
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5712. Min Range: -5.5712
Max Act: 5.3837. Min Act: -0.1700
Data Index: 5429424 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5712. Min Range: -5.5712
Max Act: 5.3524. Min Act: -0.1700
Data Index: 2568875 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5712. Min Range: -5.5712
Max Act: 5.3524. Min Act: -0.1700
Data Index: 6543140 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #19