Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4375 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.9067. Min Range: -5.9067
Max Act: 5.9067. Min Act: -0.1700
Data Index: 7392359 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9067. Min Range: -5.9067
Max Act: 5.8442. Min Act: -0.1700
Data Index: 2266981 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9067. Min Range: -5.9067
Max Act: 5.7192. Min Act: -0.1700
Data Index: 7986468 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9067. Min Range: -5.9067
Max Act: 5.6880. Min Act: -0.1700
Data Index: 6495117 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9067. Min Range: -5.9067
Max Act: 5.6567. Min Act: -0.1700
Data Index: 6215689 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9067. Min Range: -5.9067
Max Act: 5.6880. Min Act: -0.1700
Data Index: 6933881 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9067. Min Range: -5.9067
Max Act: 5.6255. Min Act: -0.1700
Data Index: 6855412 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9067. Min Range: -5.9067
Max Act: 5.5317. Min Act: -0.1700
Data Index: 126673 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9067. Min Range: -5.9067
Max Act: 5.5317. Min Act: -0.1700
Data Index: 6809965 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9067. Min Range: -5.9067
Max Act: 5.5005. Min Act: -0.1700
Data Index: 8296486 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9067. Min Range: -5.9067
Max Act: 5.4692. Min Act: -0.1700
Data Index: 1781350 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9067. Min Range: -5.9067
Max Act: 5.4692. Min Act: -0.1700
Data Index: 5429238 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9067. Min Range: -5.9067
Max Act: 5.4692. Min Act: -0.1700
Data Index: 2090959 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9067. Min Range: -5.9067
Max Act: 5.4380. Min Act: -0.1700
Data Index: 3427562 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9067. Min Range: -5.9067
Max Act: 5.4380. Min Act: -0.1700
Data Index: 6014689 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9067. Min Range: -5.9067
Max Act: 5.4067. Min Act: -0.1700
Data Index: 6131376 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9067. Min Range: -5.9067
Max Act: 5.4380. Min Act: -0.1700
Data Index: 7392358 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9067. Min Range: -5.9067
Max Act: 5.4067. Min Act: -0.1700
Data Index: 3979380 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9067. Min Range: -5.9067
Max Act: 5.3755. Min Act: -0.1700
Data Index: 1277926 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9067. Min Range: -5.9067
Max Act: 5.3442. Min Act: -0.1700
Data Index: 4226240 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #19