Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1613 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8597. Min Range: -2.8597
Max Act: 2.8597. Min Act: -0.1700
Data Index: 758800 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8597. Min Range: -2.8597
Max Act: 2.8597. Min Act: -0.1700
Data Index: 2207534 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8597. Min Range: -2.8597
Max Act: 2.8597. Min Act: -0.1700
Data Index: 8473757 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8597. Min Range: -2.8597
Max Act: 2.8438. Min Act: -0.1700
Data Index: 4463020 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8597. Min Range: -2.8597
Max Act: 2.8438. Min Act: -0.1700
Data Index: 4253471 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8597. Min Range: -2.8597
Max Act: 2.8279. Min Act: -0.1700
Data Index: 6103176 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8597. Min Range: -2.8597
Max Act: 2.8279. Min Act: -0.1700
Data Index: 2264081 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8597. Min Range: -2.8597
Max Act: 2.8279. Min Act: -0.1700
Data Index: 56694 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8597. Min Range: -2.8597
Max Act: 2.8279. Min Act: -0.1700
Data Index: 6918176 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8597. Min Range: -2.8597
Max Act: 2.8279. Min Act: -0.1700
Data Index: 3874164 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8597. Min Range: -2.8597
Max Act: 2.8279. Min Act: -0.1700
Data Index: 6036938 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8597. Min Range: -2.8597
Max Act: 2.8120. Min Act: -0.1700
Data Index: 7945972 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8597. Min Range: -2.8597
Max Act: 2.8120. Min Act: -0.1700
Data Index: 1704195 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8597. Min Range: -2.8597
Max Act: 2.8120. Min Act: -0.1700
Data Index: 1658107 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8597. Min Range: -2.8597
Max Act: 2.8120. Min Act: -0.1700
Data Index: 798315 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8597. Min Range: -2.8597
Max Act: 2.8120. Min Act: -0.1700
Data Index: 4630846 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8597. Min Range: -2.8597
Max Act: 2.7961. Min Act: -0.1700
Data Index: 3340654 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8597. Min Range: -2.8597
Max Act: 2.7961. Min Act: -0.1700
Data Index: 2377973 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8597. Min Range: -2.8597
Max Act: 2.7961. Min Act: -0.1700
Data Index: 1882350 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8597. Min Range: -2.8597
Max Act: 2.7961. Min Act: -0.1700
Data Index: 5470817 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #19