Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3486 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5046. Min Range: -4.5046
Max Act: 4.5046. Min Act: -0.1700
Data Index: 4515657 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5046. Min Range: -4.5046
Max Act: 4.4734. Min Act: -0.1700
Data Index: 5933987 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5046. Min Range: -4.5046
Max Act: 4.4108. Min Act: -0.1700
Data Index: 7394509 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5046. Min Range: -4.5046
Max Act: 4.4108. Min Act: -0.1700
Data Index: 5337178 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5046. Min Range: -4.5046
Max Act: 4.4108. Min Act: -0.1700
Data Index: 7838944 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5046. Min Range: -4.5046
Max Act: 4.3483. Min Act: -0.1700
Data Index: 439876 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5046. Min Range: -4.5046
Max Act: 4.3483. Min Act: -0.1700
Data Index: 6471672 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5046. Min Range: -4.5046
Max Act: 4.3171. Min Act: -0.1700
Data Index: 5772762 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5046. Min Range: -4.5046
Max Act: 4.3171. Min Act: -0.1700
Data Index: 2332063 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5046. Min Range: -4.5046
Max Act: 4.2858. Min Act: -0.1700
Data Index: 836154 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5046. Min Range: -4.5046
Max Act: 4.2233. Min Act: -0.1700
Data Index: 4083496 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5046. Min Range: -4.5046
Max Act: 4.2546. Min Act: -0.1700
Data Index: 6471673 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5046. Min Range: -4.5046
Max Act: 4.2546. Min Act: -0.1700
Data Index: 6226824 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5046. Min Range: -4.5046
Max Act: 4.2546. Min Act: -0.1700
Data Index: 1547859 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5046. Min Range: -4.5046
Max Act: 4.2546. Min Act: -0.1700
Data Index: 3298678 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5046. Min Range: -4.5046
Max Act: 4.2233. Min Act: -0.1700
Data Index: 6208791 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5046. Min Range: -4.5046
Max Act: 4.2233. Min Act: -0.1700
Data Index: 7082496 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5046. Min Range: -4.5046
Max Act: 4.2233. Min Act: -0.1700
Data Index: 4504416 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5046. Min Range: -4.5046
Max Act: 4.2233. Min Act: -0.1700
Data Index: 4397537 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5046. Min Range: -4.5046
Max Act: 4.2233. Min Act: -0.1700
Data Index: 3591400 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #19