Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2107 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.6922. Min Range: -3.6922
Max Act: 3.6922. Min Act: -0.1700
Data Index: 2723225 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6922. Min Range: -3.6922
Max Act: 3.6609. Min Act: -0.1700
Data Index: 6532877 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6922. Min Range: -3.6922
Max Act: 3.6296. Min Act: -0.1700
Data Index: 7533899 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6922. Min Range: -3.6922
Max Act: 3.5983. Min Act: -0.1700
Data Index: 2300831 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6922. Min Range: -3.6922
Max Act: 3.6296. Min Act: -0.1700
Data Index: 4643774 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6922. Min Range: -3.6922
Max Act: 3.5983. Min Act: -0.1700
Data Index: 2975919 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6922. Min Range: -3.6922
Max Act: 3.5670. Min Act: -0.1700
Data Index: 5242375 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6922. Min Range: -3.6922
Max Act: 3.5983. Min Act: -0.1700
Data Index: 4905275 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6922. Min Range: -3.6922
Max Act: 3.6296. Min Act: -0.1700
Data Index: 8723603 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6922. Min Range: -3.6922
Max Act: 3.6296. Min Act: -0.1700
Data Index: 3559688 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6922. Min Range: -3.6922
Max Act: 3.5670. Min Act: -0.1700
Data Index: 898918 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6922. Min Range: -3.6922
Max Act: 3.5670. Min Act: -0.1700
Data Index: 5123515 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6922. Min Range: -3.6922
Max Act: 3.5670. Min Act: -0.1700
Data Index: 6270790 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6922. Min Range: -3.6922
Max Act: 3.5670. Min Act: -0.1700
Data Index: 4281068 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6922. Min Range: -3.6922
Max Act: 3.5670. Min Act: -0.1700
Data Index: 42249 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6922. Min Range: -3.6922
Max Act: 3.5357. Min Act: -0.1700
Data Index: 7595509 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6922. Min Range: -3.6922
Max Act: 3.5357. Min Act: -0.1700
Data Index: 1242375 (Open Web Text)
Max Activating Token Index: 239
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6922. Min Range: -3.6922
Max Act: 3.5357. Min Act: -0.1700
Data Index: 7266749 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6922. Min Range: -3.6922
Max Act: 3.5357. Min Act: -0.1700
Data Index: 6111217 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6922. Min Range: -3.6922
Max Act: 3.5200. Min Act: -0.1700
Data Index: 4495584 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #19