Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 221 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 1.7527. Min Range: -1.7527
Max Act: 1.7527. Min Act: -0.1700
Data Index: 287484 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7527. Min Range: -1.7527
Max Act: 1.6747. Min Act: -0.1699
Data Index: 7138939 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7527. Min Range: -1.7527
Max Act: 1.6660. Min Act: -0.1700
Data Index: 8726539 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7527. Min Range: -1.7527
Max Act: 1.6660. Min Act: -0.1700
Data Index: 5322000 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7527. Min Range: -1.7527
Max Act: 1.6747. Min Act: -0.1699
Data Index: 1922339 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7527. Min Range: -1.7527
Max Act: 1.6660. Min Act: -0.1697
Data Index: 6550237 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7527. Min Range: -1.7527
Max Act: 1.6747. Min Act: -0.1700
Data Index: 2955129 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7527. Min Range: -1.7527
Max Act: 1.6486. Min Act: -0.1700
Data Index: 6633585 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7527. Min Range: -1.7527
Max Act: 1.6573. Min Act: -0.1699
Data Index: 4875362 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7527. Min Range: -1.7527
Max Act: 1.6486. Min Act: -0.1700
Data Index: 6388801 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7527. Min Range: -1.7527
Max Act: 1.6486. Min Act: -0.1700
Data Index: 3542353 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7527. Min Range: -1.7527
Max Act: 1.6486. Min Act: -0.1696
Data Index: 3083487 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7527. Min Range: -1.7527
Max Act: 1.6399. Min Act: -0.1700
Data Index: 4975597 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7527. Min Range: -1.7527
Max Act: 1.6486. Min Act: -0.1700
Data Index: 7652242 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7527. Min Range: -1.7527
Max Act: 1.6399. Min Act: -0.1700
Data Index: 734931 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7527. Min Range: -1.7527
Max Act: 1.6399. Min Act: -0.1700
Data Index: 7522637 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7527. Min Range: -1.7527
Max Act: 1.6312. Min Act: -0.1699
Data Index: 8582190 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7527. Min Range: -1.7527
Max Act: 1.6399. Min Act: -0.1700
Data Index: 6798027 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7527. Min Range: -1.7527
Max Act: 1.6399. Min Act: -0.1700
Data Index: 5281912 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7527. Min Range: -1.7527
Max Act: 1.6312. Min Act: -0.1700
Data Index: 8049743 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #19