Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 915 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5843. Min Range: -7.5843
Max Act: 7.5843. Min Act: -0.1700
Data Index: 889281 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5843. Min Range: -7.5843
Max Act: 7.4593. Min Act: -0.1700
Data Index: 2292623 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5843. Min Range: -7.5843
Max Act: 7.3968. Min Act: -0.1700
Data Index: 3193196 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5843. Min Range: -7.5843
Max Act: 7.3968. Min Act: -0.1700
Data Index: 2973848 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5843. Min Range: -7.5843
Max Act: 7.3655. Min Act: -0.1700
Data Index: 4236003 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5843. Min Range: -7.5843
Max Act: 7.3655. Min Act: -0.1700
Data Index: 3489245 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5843. Min Range: -7.5843
Max Act: 7.3343. Min Act: -0.1700
Data Index: 7105677 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5843. Min Range: -7.5843
Max Act: 7.3343. Min Act: -0.1700
Data Index: 7062785 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5843. Min Range: -7.5843
Max Act: 7.3030. Min Act: -0.1700
Data Index: 7730307 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5843. Min Range: -7.5843
Max Act: 7.3030. Min Act: -0.1700
Data Index: 2895360 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5843. Min Range: -7.5843
Max Act: 7.2405. Min Act: -0.1700
Data Index: 7577315 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5843. Min Range: -7.5843
Max Act: 7.2718. Min Act: -0.1700
Data Index: 4236002 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5843. Min Range: -7.5843
Max Act: 7.2718. Min Act: -0.1700
Data Index: 4156752 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5843. Min Range: -7.5843
Max Act: 7.2405. Min Act: -0.1700
Data Index: 3027472 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5843. Min Range: -7.5843
Max Act: 7.2093. Min Act: -0.1700
Data Index: 2895357 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5843. Min Range: -7.5843
Max Act: 7.2093. Min Act: -0.1700
Data Index: 1593766 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5843. Min Range: -7.5843
Max Act: 7.2093. Min Act: -0.1700
Data Index: 8263356 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5843. Min Range: -7.5843
Max Act: 7.2093. Min Act: -0.1700
Data Index: 8485389 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5843. Min Range: -7.5843
Max Act: 7.1468. Min Act: -0.1700
Data Index: 4087901 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5843. Min Range: -7.5843
Max Act: 7.1780. Min Act: -0.1700
Data Index: 6281965 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #19