Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5408 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5322. Min Range: -6.5322
Max Act: 6.5322. Min Act: -0.1700
Data Index: 1322427 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5322. Min Range: -6.5322
Max Act: 6.4384. Min Act: -0.1700
Data Index: 2529276 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5322. Min Range: -6.5322
Max Act: 6.3447. Min Act: -0.1700
Data Index: 3196916 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5322. Min Range: -6.5322
Max Act: 6.3134. Min Act: -0.1700
Data Index: 4392537 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5322. Min Range: -6.5322
Max Act: 6.2822. Min Act: -0.1700
Data Index: 2106270 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5322. Min Range: -6.5322
Max Act: 6.2509. Min Act: -0.1700
Data Index: 838106 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5322. Min Range: -6.5322
Max Act: 6.2197. Min Act: -0.1700
Data Index: 6859531 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5322. Min Range: -6.5322
Max Act: 6.2197. Min Act: -0.1700
Data Index: 6369475 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5322. Min Range: -6.5322
Max Act: 6.1884. Min Act: -0.1700
Data Index: 7915740 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5322. Min Range: -6.5322
Max Act: 6.1884. Min Act: -0.1700
Data Index: 1901336 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5322. Min Range: -6.5322
Max Act: 6.0947. Min Act: -0.1700
Data Index: 5386231 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5322. Min Range: -6.5322
Max Act: 6.0947. Min Act: -0.1700
Data Index: 8335012 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5322. Min Range: -6.5322
Max Act: 6.0947. Min Act: -0.1700
Data Index: 5865065 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5322. Min Range: -6.5322
Max Act: 6.1259. Min Act: -0.1700
Data Index: 6687931 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5322. Min Range: -6.5322
Max Act: 6.0947. Min Act: -0.1700
Data Index: 8435253 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5322. Min Range: -6.5322
Max Act: 6.0947. Min Act: -0.1700
Data Index: 6082792 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5322. Min Range: -6.5322
Max Act: 6.0947. Min Act: -0.1700
Data Index: 1475584 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5322. Min Range: -6.5322
Max Act: 6.0947. Min Act: -0.1700
Data Index: 2132652 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5322. Min Range: -6.5322
Max Act: 6.0947. Min Act: -0.1700
Data Index: 333680 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5322. Min Range: -6.5322
Max Act: 6.0634. Min Act: -0.1700
Data Index: 849479 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #19