Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3359 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6482. Min Range: -7.6482
Max Act: 7.6482. Min Act: -0.1700
Data Index: 1044502 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6482. Min Range: -7.6482
Max Act: 7.1794. Min Act: -0.1700
Data Index: 3577251 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6482. Min Range: -7.6482
Max Act: 7.0544. Min Act: -0.1700
Data Index: 8566247 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6482. Min Range: -7.6482
Max Act: 7.0232. Min Act: -0.1700
Data Index: 973012 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6482. Min Range: -7.6482
Max Act: 6.9607. Min Act: -0.1700
Data Index: 1977195 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6482. Min Range: -7.6482
Max Act: 6.8982. Min Act: -0.1700
Data Index: 7332189 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6482. Min Range: -7.6482
Max Act: 6.8982. Min Act: -0.1700
Data Index: 1248191 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6482. Min Range: -7.6482
Max Act: 6.8982. Min Act: -0.1700
Data Index: 5189420 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6482. Min Range: -7.6482
Max Act: 6.8357. Min Act: -0.1700
Data Index: 8339149 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6482. Min Range: -7.6482
Max Act: 6.7419. Min Act: -0.1700
Data Index: 650083 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6482. Min Range: -7.6482
Max Act: 6.7732. Min Act: -0.1700
Data Index: 7640536 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6482. Min Range: -7.6482
Max Act: 6.7419. Min Act: -0.1700
Data Index: 1749396 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6482. Min Range: -7.6482
Max Act: 6.7107. Min Act: -0.1700
Data Index: 73885 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6482. Min Range: -7.6482
Max Act: 6.6794. Min Act: -0.1700
Data Index: 7426051 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6482. Min Range: -7.6482
Max Act: 6.6482. Min Act: -0.1700
Data Index: 5135804 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6482. Min Range: -7.6482
Max Act: 6.6482. Min Act: -0.1700
Data Index: 3628461 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6482. Min Range: -7.6482
Max Act: 6.6482. Min Act: -0.1700
Data Index: 2740191 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6482. Min Range: -7.6482
Max Act: 6.6482. Min Act: -0.1700
Data Index: 3440026 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6482. Min Range: -7.6482
Max Act: 6.6169. Min Act: -0.1700
Data Index: 6429102 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6482. Min Range: -7.6482
Max Act: 6.6169. Min Act: -0.1700
Data Index: 2437119 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #19