Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1422 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.2205. Min Range: -7.2205
Max Act: 7.2205. Min Act: -0.1700
Data Index: 729757 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2205. Min Range: -7.2205
Max Act: 7.0330. Min Act: -0.1700
Data Index: 2116092 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2205. Min Range: -7.2205
Max Act: 6.8455. Min Act: -0.1700
Data Index: 5859963 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2205. Min Range: -7.2205
Max Act: 6.8767. Min Act: -0.1700
Data Index: 1323646 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2205. Min Range: -7.2205
Max Act: 6.8455. Min Act: -0.1700
Data Index: 8773053 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2205. Min Range: -7.2205
Max Act: 6.7205. Min Act: -0.1700
Data Index: 6386185 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2205. Min Range: -7.2205
Max Act: 6.7205. Min Act: -0.1700
Data Index: 5522742 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2205. Min Range: -7.2205
Max Act: 6.6892. Min Act: -0.1700
Data Index: 5452796 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2205. Min Range: -7.2205
Max Act: 6.6267. Min Act: -0.1700
Data Index: 5452793 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2205. Min Range: -7.2205
Max Act: 6.6267. Min Act: -0.1700
Data Index: 2091941 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2205. Min Range: -7.2205
Max Act: 6.5955. Min Act: -0.1700
Data Index: 4513442 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2205. Min Range: -7.2205
Max Act: 6.5955. Min Act: -0.1700
Data Index: 5504456 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2205. Min Range: -7.2205
Max Act: 6.6267. Min Act: -0.1700
Data Index: 6386188 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2205. Min Range: -7.2205
Max Act: 6.6267. Min Act: -0.1700
Data Index: 5504453 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2205. Min Range: -7.2205
Max Act: 6.5642. Min Act: -0.1700
Data Index: 6786966 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2205. Min Range: -7.2205
Max Act: 6.5955. Min Act: -0.1700
Data Index: 4249623 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2205. Min Range: -7.2205
Max Act: 6.5955. Min Act: -0.1700
Data Index: 374244 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2205. Min Range: -7.2205
Max Act: 6.6580. Min Act: -0.1700
Data Index: 3089469 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2205. Min Range: -7.2205
Max Act: 6.5330. Min Act: -0.1700
Data Index: 858781 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2205. Min Range: -7.2205
Max Act: 6.4705. Min Act: -0.1700
Data Index: 5809810 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #19