Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1985 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4825. Min Range: -3.4825
Max Act: 3.4825. Min Act: -0.1700
Data Index: 4719906 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4825. Min Range: -3.4825
Max Act: 3.4198. Min Act: -0.1700
Data Index: 4123584 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4825. Min Range: -3.4825
Max Act: 3.4041. Min Act: -0.1700
Data Index: 584052 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4825. Min Range: -3.4825
Max Act: 3.3728. Min Act: -0.1700
Data Index: 5872092 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4825. Min Range: -3.4825
Max Act: 3.3257. Min Act: -0.1700
Data Index: 8442824 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4825. Min Range: -3.4825
Max Act: 3.2943. Min Act: -0.1700
Data Index: 1341607 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4825. Min Range: -3.4825
Max Act: 3.3257. Min Act: -0.1700
Data Index: 3951116 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4825. Min Range: -3.4825
Max Act: 3.3100. Min Act: -0.1700
Data Index: 6068582 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4825. Min Range: -3.4825
Max Act: 3.2786. Min Act: -0.1700
Data Index: 3854615 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4825. Min Range: -3.4825
Max Act: 3.2472. Min Act: -0.1700
Data Index: 6786081 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4825. Min Range: -3.4825
Max Act: 3.2158. Min Act: -0.1700
Data Index: 5243336 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4825. Min Range: -3.4825
Max Act: 3.2315. Min Act: -0.1700
Data Index: 1534350 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4825. Min Range: -3.4825
Max Act: 3.2000. Min Act: -0.1700
Data Index: 1453434 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4825. Min Range: -3.4825
Max Act: 3.2000. Min Act: -0.1700
Data Index: 8700681 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4825. Min Range: -3.4825
Max Act: 3.1843. Min Act: -0.1700
Data Index: 3563056 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4825. Min Range: -3.4825
Max Act: 3.1528. Min Act: -0.1700
Data Index: 5899126 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4825. Min Range: -3.4825
Max Act: 3.1686. Min Act: -0.1700
Data Index: 6598190 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4825. Min Range: -3.4825
Max Act: 3.1843. Min Act: -0.1700
Data Index: 4632892 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4825. Min Range: -3.4825
Max Act: 3.1686. Min Act: -0.1700
Data Index: 2968371 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4825. Min Range: -3.4825
Max Act: 3.1686. Min Act: -0.1700
Data Index: 2668466 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19