Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3448 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0233. Min Range: -6.0233
Max Act: 6.0233. Min Act: -0.1700
Data Index: 2519315 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0233. Min Range: -6.0233
Max Act: 5.9295. Min Act: -0.1700
Data Index: 3306832 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0233. Min Range: -6.0233
Max Act: 5.9295. Min Act: -0.1700
Data Index: 8409585 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0233. Min Range: -6.0233
Max Act: 5.8983. Min Act: -0.1700
Data Index: 8109 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0233. Min Range: -6.0233
Max Act: 5.7733. Min Act: -0.1700
Data Index: 5159463 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0233. Min Range: -6.0233
Max Act: 5.7108. Min Act: -0.1700
Data Index: 1876774 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0233. Min Range: -6.0233
Max Act: 5.6795. Min Act: -0.1700
Data Index: 984122 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0233. Min Range: -6.0233
Max Act: 5.6170. Min Act: -0.1700
Data Index: 4951980 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0233. Min Range: -6.0233
Max Act: 5.6170. Min Act: -0.1700
Data Index: 1940601 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0233. Min Range: -6.0233
Max Act: 5.5858. Min Act: -0.1700
Data Index: 5349008 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0233. Min Range: -6.0233
Max Act: 5.5545. Min Act: -0.1700
Data Index: 6592115 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0233. Min Range: -6.0233
Max Act: 5.5233. Min Act: -0.1700
Data Index: 4918018 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0233. Min Range: -6.0233
Max Act: 5.5233. Min Act: -0.1700
Data Index: 6629145 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0233. Min Range: -6.0233
Max Act: 5.5233. Min Act: -0.1700
Data Index: 3576744 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0233. Min Range: -6.0233
Max Act: 5.5233. Min Act: -0.1700
Data Index: 4719307 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0233. Min Range: -6.0233
Max Act: 5.4920. Min Act: -0.1700
Data Index: 8284696 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0233. Min Range: -6.0233
Max Act: 5.5233. Min Act: -0.1700
Data Index: 2739346 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0233. Min Range: -6.0233
Max Act: 5.4608. Min Act: -0.1700
Data Index: 1244770 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0233. Min Range: -6.0233
Max Act: 5.4608. Min Act: -0.1700
Data Index: 3084309 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0233. Min Range: -6.0233
Max Act: 5.3983. Min Act: -0.1700
Data Index: 4173532 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #19