Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3582 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6670. Min Range: -5.6670
Max Act: 5.6670. Min Act: -0.1700
Data Index: 2404376 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6670. Min Range: -5.6670
Max Act: 5.6357. Min Act: -0.1700
Data Index: 4930837 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6670. Min Range: -5.6670
Max Act: 5.6045. Min Act: -0.1700
Data Index: 2627873 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6670. Min Range: -5.6670
Max Act: 5.5107. Min Act: -0.1700
Data Index: 1917586 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6670. Min Range: -5.6670
Max Act: 5.5107. Min Act: -0.1700
Data Index: 2073752 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6670. Min Range: -5.6670
Max Act: 5.4795. Min Act: -0.1700
Data Index: 7379796 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6670. Min Range: -5.6670
Max Act: 5.4795. Min Act: -0.1700
Data Index: 5970096 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6670. Min Range: -5.6670
Max Act: 5.4170. Min Act: -0.1700
Data Index: 8486681 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6670. Min Range: -5.6670
Max Act: 5.4170. Min Act: -0.1700
Data Index: 118401 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6670. Min Range: -5.6670
Max Act: 5.4170. Min Act: -0.1700
Data Index: 8205018 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6670. Min Range: -5.6670
Max Act: 5.4170. Min Act: -0.1700
Data Index: 8486680 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6670. Min Range: -5.6670
Max Act: 5.3857. Min Act: -0.1700
Data Index: 3564715 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6670. Min Range: -5.6670
Max Act: 5.3857. Min Act: -0.1700
Data Index: 3074626 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6670. Min Range: -5.6670
Max Act: 5.3545. Min Act: -0.1700
Data Index: 7176153 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6670. Min Range: -5.6670
Max Act: 5.3232. Min Act: -0.1700
Data Index: 2718001 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6670. Min Range: -5.6670
Max Act: 5.3232. Min Act: -0.1700
Data Index: 2484874 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6670. Min Range: -5.6670
Max Act: 5.3232. Min Act: -0.1700
Data Index: 2418668 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6670. Min Range: -5.6670
Max Act: 5.3232. Min Act: -0.1700
Data Index: 2610128 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6670. Min Range: -5.6670
Max Act: 5.2920. Min Act: -0.1700
Data Index: 1816243 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6670. Min Range: -5.6670
Max Act: 5.2920. Min Act: -0.1700
Data Index: 4681182 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19