Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2217 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.0088. Min Range: -2.0088
Max Act: 2.0088. Min Act: -0.1700
Data Index: 3232587 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0088. Min Range: -2.0088
Max Act: 1.9411. Min Act: -0.1700
Data Index: 2572625 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0088. Min Range: -2.0088
Max Act: 1.9241. Min Act: -0.1700
Data Index: 7342264 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0088. Min Range: -2.0088
Max Act: 1.9070. Min Act: -0.1700
Data Index: 1225348 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0088. Min Range: -2.0088
Max Act: 1.8558. Min Act: -0.1700
Data Index: 7921689 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0088. Min Range: -2.0088
Max Act: 1.8729. Min Act: -0.1700
Data Index: 8829096 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0088. Min Range: -2.0088
Max Act: 1.8558. Min Act: -0.1700
Data Index: 8108629 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0088. Min Range: -2.0088
Max Act: 1.8558. Min Act: -0.1700
Data Index: 1010963 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0088. Min Range: -2.0088
Max Act: 1.8387. Min Act: -0.1700
Data Index: 3720158 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0088. Min Range: -2.0088
Max Act: 1.8387. Min Act: -0.1700
Data Index: 440325 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0088. Min Range: -2.0088
Max Act: 1.8043. Min Act: -0.1700
Data Index: 1992978 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0088. Min Range: -2.0088
Max Act: 1.8043. Min Act: -0.1700
Data Index: 2486901 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0088. Min Range: -2.0088
Max Act: 1.7871. Min Act: -0.1700
Data Index: 385314 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0088. Min Range: -2.0088
Max Act: 1.7526. Min Act: -0.1700
Data Index: 7482542 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0088. Min Range: -2.0088
Max Act: 1.7526. Min Act: -0.1700
Data Index: 7082607 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0088. Min Range: -2.0088
Max Act: 1.7526. Min Act: -0.1700
Data Index: 8028561 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0088. Min Range: -2.0088
Max Act: 1.7353. Min Act: -0.1700
Data Index: 3008062 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0088. Min Range: -2.0088
Max Act: 1.7180. Min Act: -0.1700
Data Index: 4233902 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0088. Min Range: -2.0088
Max Act: 1.7180. Min Act: -0.1700
Data Index: 4572034 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0088. Min Range: -2.0088
Max Act: 1.7180. Min Act: -0.1700
Data Index: 1385840 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #19