Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2520 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 8.4206. Min Range: -8.4206
Max Act: 8.4206. Min Act: -0.1700
Data Index: 1990566 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4206. Min Range: -8.4206
Max Act: 8.2956. Min Act: -0.1700
Data Index: 4165388 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4206. Min Range: -8.4206
Max Act: 8.1706. Min Act: -0.1700
Data Index: 8795995 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4206. Min Range: -8.4206
Max Act: 8.1081. Min Act: -0.1700
Data Index: 5156641 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4206. Min Range: -8.4206
Max Act: 8.0456. Min Act: -0.1700
Data Index: 8744931 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4206. Min Range: -8.4206
Max Act: 7.9206. Min Act: -0.1700
Data Index: 7468274 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4206. Min Range: -8.4206
Max Act: 7.9519. Min Act: -0.1700
Data Index: 1186853 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4206. Min Range: -8.4206
Max Act: 7.9206. Min Act: -0.1700
Data Index: 1904548 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4206. Min Range: -8.4206
Max Act: 7.9206. Min Act: -0.1700
Data Index: 8564976 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4206. Min Range: -8.4206
Max Act: 7.8581. Min Act: -0.1700
Data Index: 5054366 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4206. Min Range: -8.4206
Max Act: 7.9206. Min Act: -0.1700
Data Index: 5156643 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4206. Min Range: -8.4206
Max Act: 7.7956. Min Act: -0.1700
Data Index: 6476965 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4206. Min Range: -8.4206
Max Act: 7.7956. Min Act: -0.1700
Data Index: 5457313 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4206. Min Range: -8.4206
Max Act: 7.7956. Min Act: -0.1700
Data Index: 4917631 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4206. Min Range: -8.4206
Max Act: 7.7956. Min Act: -0.1700
Data Index: 8683392 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4206. Min Range: -8.4206
Max Act: 7.7644. Min Act: -0.1700
Data Index: 3420039 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4206. Min Range: -8.4206
Max Act: 7.7644. Min Act: -0.1700
Data Index: 7487409 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4206. Min Range: -8.4206
Max Act: 7.7331. Min Act: -0.1700
Data Index: 6944647 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4206. Min Range: -8.4206
Max Act: 7.6706. Min Act: -0.1700
Data Index: 6476967 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4206. Min Range: -8.4206
Max Act: 7.7331. Min Act: -0.1700
Data Index: 6109382 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19