Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 797 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2212. Min Range: -5.2212
Max Act: 5.2212. Min Act: -0.1700
Data Index: 7639959 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.7837. Min Act: -0.1700
Data Index: 4526159 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.7212. Min Act: -0.1700
Data Index: 241012 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.7212. Min Act: -0.1700
Data Index: 658141 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.6899. Min Act: -0.1700
Data Index: 4801302 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.6899. Min Act: -0.1700
Data Index: 2157123 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.6899. Min Act: -0.1700
Data Index: 349175 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.6587. Min Act: -0.1700
Data Index: 5011343 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.6587. Min Act: -0.1700
Data Index: 492138 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.6587. Min Act: -0.1700
Data Index: 4358177 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.6587. Min Act: -0.1700
Data Index: 8001484 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.6587. Min Act: -0.1700
Data Index: 5460178 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.6587. Min Act: -0.1700
Data Index: 2346957 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.6587. Min Act: -0.1700
Data Index: 2463806 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.5649. Min Act: -0.1700
Data Index: 2360483 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.5962. Min Act: -0.1700
Data Index: 7378134 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.5962. Min Act: -0.1700
Data Index: 4446107 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.5649. Min Act: -0.1700
Data Index: 5167202 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.5649. Min Act: -0.1700
Data Index: 2431791 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2212. Min Range: -5.2212
Max Act: 4.5337. Min Act: -0.1700
Data Index: 6762022 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #19