Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4256 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7906. Min Range: -7.7906
Max Act: 7.7906. Min Act: -0.1700
Data Index: 688693 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7906. Min Range: -7.7906
Max Act: 7.6343. Min Act: -0.1700
Data Index: 7191110 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7906. Min Range: -7.7906
Max Act: 7.5093. Min Act: -0.1700
Data Index: 2061749 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7906. Min Range: -7.7906
Max Act: 7.4468. Min Act: -0.1700
Data Index: 1122965 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7906. Min Range: -7.7906
Max Act: 7.4468. Min Act: -0.1700
Data Index: 8308927 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7906. Min Range: -7.7906
Max Act: 7.4468. Min Act: -0.1700
Data Index: 7651281 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7906. Min Range: -7.7906
Max Act: 7.4468. Min Act: -0.1700
Data Index: 4992515 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7906. Min Range: -7.7906
Max Act: 7.4156. Min Act: -0.1700
Data Index: 1894019 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7906. Min Range: -7.7906
Max Act: 7.3531. Min Act: -0.1700
Data Index: 8667595 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7906. Min Range: -7.7906
Max Act: 7.3218. Min Act: -0.1700
Data Index: 5390400 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7906. Min Range: -7.7906
Max Act: 7.2593. Min Act: -0.1700
Data Index: 8114211 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7906. Min Range: -7.7906
Max Act: 7.2906. Min Act: -0.1700
Data Index: 6388546 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7906. Min Range: -7.7906
Max Act: 7.2906. Min Act: -0.1700
Data Index: 2317811 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7906. Min Range: -7.7906
Max Act: 7.2593. Min Act: -0.1700
Data Index: 6960634 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7906. Min Range: -7.7906
Max Act: 7.2593. Min Act: -0.1700
Data Index: 8736040 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7906. Min Range: -7.7906
Max Act: 7.2593. Min Act: -0.1700
Data Index: 1267305 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7906. Min Range: -7.7906
Max Act: 7.2593. Min Act: -0.1700
Data Index: 451194 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7906. Min Range: -7.7906
Max Act: 7.2906. Min Act: -0.1700
Data Index: 6174171 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7906. Min Range: -7.7906
Max Act: 7.2281. Min Act: -0.1700
Data Index: 7573173 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7906. Min Range: -7.7906
Max Act: 7.2281. Min Act: -0.1700
Data Index: 4381884 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #19