Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1527 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3749. Min Range: -5.3749
Max Act: 5.3749. Min Act: -0.1700
Data Index: 2269575 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3749. Min Range: -5.3749
Max Act: 5.3124. Min Act: -0.1700
Data Index: 4198051 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3749. Min Range: -5.3749
Max Act: 5.2499. Min Act: -0.1700
Data Index: 6791456 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3749. Min Range: -5.3749
Max Act: 5.2499. Min Act: -0.1700
Data Index: 2571557 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3749. Min Range: -5.3749
Max Act: 5.2187. Min Act: -0.1700
Data Index: 3491380 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3749. Min Range: -5.3749
Max Act: 5.1562. Min Act: -0.1700
Data Index: 2571533 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3749. Min Range: -5.3749
Max Act: 5.1874. Min Act: -0.1700
Data Index: 1494146 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3749. Min Range: -5.3749
Max Act: 5.1562. Min Act: -0.1700
Data Index: 8051382 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3749. Min Range: -5.3749
Max Act: 5.0937. Min Act: -0.1700
Data Index: 7621887 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3749. Min Range: -5.3749
Max Act: 5.0937. Min Act: -0.1700
Data Index: 6586597 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3749. Min Range: -5.3749
Max Act: 5.0937. Min Act: -0.1700
Data Index: 1078725 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3749. Min Range: -5.3749
Max Act: 5.0312. Min Act: -0.1700
Data Index: 1227548 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3749. Min Range: -5.3749
Max Act: 5.0624. Min Act: -0.1700
Data Index: 285984 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3749. Min Range: -5.3749
Max Act: 5.0624. Min Act: -0.1700
Data Index: 2225768 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3749. Min Range: -5.3749
Max Act: 5.0312. Min Act: -0.1700
Data Index: 7927500 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3749. Min Range: -5.3749
Max Act: 5.0312. Min Act: -0.1700
Data Index: 1186820 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3749. Min Range: -5.3749
Max Act: 5.0312. Min Act: -0.1700
Data Index: 8772109 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3749. Min Range: -5.3749
Max Act: 4.9687. Min Act: -0.1700
Data Index: 8439053 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3749. Min Range: -5.3749
Max Act: 4.9687. Min Act: -0.1700
Data Index: 7013323 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3749. Min Range: -5.3749
Max Act: 4.9687. Min Act: -0.1700
Data Index: 1862569 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #19