Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3564 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3492. Min Range: -7.3492
Max Act: 7.3492. Min Act: -0.1700
Data Index: 5208638 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3492. Min Range: -7.3492
Max Act: 7.1930. Min Act: -0.1700
Data Index: 1283486 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3492. Min Range: -7.3492
Max Act: 6.9430. Min Act: -0.1700
Data Index: 2628414 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3492. Min Range: -7.3492
Max Act: 6.8805. Min Act: -0.1700
Data Index: 5550555 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3492. Min Range: -7.3492
Max Act: 6.8492. Min Act: -0.1700
Data Index: 528942 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3492. Min Range: -7.3492
Max Act: 6.8180. Min Act: -0.1700
Data Index: 3644065 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3492. Min Range: -7.3492
Max Act: 6.8180. Min Act: -0.1700
Data Index: 4365604 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3492. Min Range: -7.3492
Max Act: 6.7555. Min Act: -0.1700
Data Index: 1736093 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3492. Min Range: -7.3492
Max Act: 6.7555. Min Act: -0.1700
Data Index: 7560388 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3492. Min Range: -7.3492
Max Act: 6.6930. Min Act: -0.1700
Data Index: 4968072 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3492. Min Range: -7.3492
Max Act: 6.7242. Min Act: -0.1700
Data Index: 2481963 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3492. Min Range: -7.3492
Max Act: 6.6930. Min Act: -0.1700
Data Index: 6429778 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3492. Min Range: -7.3492
Max Act: 6.6617. Min Act: -0.1700
Data Index: 1009895 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3492. Min Range: -7.3492
Max Act: 6.6930. Min Act: -0.1700
Data Index: 5414578 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3492. Min Range: -7.3492
Max Act: 6.6305. Min Act: -0.1700
Data Index: 4078966 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3492. Min Range: -7.3492
Max Act: 6.6305. Min Act: -0.1700
Data Index: 6726774 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3492. Min Range: -7.3492
Max Act: 6.6305. Min Act: -0.1700
Data Index: 2158681 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3492. Min Range: -7.3492
Max Act: 6.6305. Min Act: -0.1700
Data Index: 1375581 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3492. Min Range: -7.3492
Max Act: 6.6305. Min Act: -0.1700
Data Index: 620793 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3492. Min Range: -7.3492
Max Act: 6.5992. Min Act: -0.1700
Data Index: 7325402 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #19