Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4079 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6062. Min Range: -9.6062
Max Act: 9.6062. Min Act: -0.1700
Data Index: 3125801 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6062. Min Range: -9.6062
Max Act: 9.2312. Min Act: -0.1700
Data Index: 2943315 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6062. Min Range: -9.6062
Max Act: 9.2312. Min Act: -0.1700
Data Index: 4982344 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6062. Min Range: -9.6062
Max Act: 9.1062. Min Act: -0.1700
Data Index: 3845443 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6062. Min Range: -9.6062
Max Act: 9.1687. Min Act: -0.1700
Data Index: 3497593 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6062. Min Range: -9.6062
Max Act: 9.0437. Min Act: -0.1700
Data Index: 1543346 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6062. Min Range: -9.6062
Max Act: 8.9812. Min Act: -0.1700
Data Index: 6801860 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6062. Min Range: -9.6062
Max Act: 8.9187. Min Act: -0.1700
Data Index: 3176214 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6062. Min Range: -9.6062
Max Act: 8.9187. Min Act: -0.1700
Data Index: 965255 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6062. Min Range: -9.6062
Max Act: 8.8562. Min Act: -0.1700
Data Index: 6628924 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6062. Min Range: -9.6062
Max Act: 8.8562. Min Act: -0.1700
Data Index: 4383527 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6062. Min Range: -9.6062
Max Act: 8.7937. Min Act: -0.1700
Data Index: 2838599 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6062. Min Range: -9.6062
Max Act: 8.7312. Min Act: -0.1700
Data Index: 2315401 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6062. Min Range: -9.6062
Max Act: 8.7312. Min Act: -0.1700
Data Index: 5811892 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6062. Min Range: -9.6062
Max Act: 8.6687. Min Act: -0.1700
Data Index: 5076777 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6062. Min Range: -9.6062
Max Act: 8.6687. Min Act: -0.1700
Data Index: 1112437 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6062. Min Range: -9.6062
Max Act: 8.6687. Min Act: -0.1700
Data Index: 7877497 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6062. Min Range: -9.6062
Max Act: 8.6687. Min Act: -0.1700
Data Index: 1775888 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6062. Min Range: -9.6062
Max Act: 8.6062. Min Act: -0.1700
Data Index: 6263465 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6062. Min Range: -9.6062
Max Act: 8.6687. Min Act: -0.1700
Data Index: 4279091 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #19