Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2868 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8890. Min Range: -3.8890
Max Act: 3.8890. Min Act: -0.1700
Data Index: 3022870 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8890. Min Range: -3.8890
Max Act: 3.8734. Min Act: -0.1700
Data Index: 7972264 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8890. Min Range: -3.8890
Max Act: 3.8109. Min Act: -0.1700
Data Index: 686269 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8890. Min Range: -3.8890
Max Act: 3.8265. Min Act: -0.1700
Data Index: 4899084 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8890. Min Range: -3.8890
Max Act: 3.7483. Min Act: -0.1700
Data Index: 625910 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8890. Min Range: -3.8890
Max Act: 3.7483. Min Act: -0.1700
Data Index: 6702385 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8890. Min Range: -3.8890
Max Act: 3.7014. Min Act: -0.1700
Data Index: 5280996 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8890. Min Range: -3.8890
Max Act: 3.7170. Min Act: -0.1700
Data Index: 6160166 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8890. Min Range: -3.8890
Max Act: 3.6857. Min Act: -0.1700
Data Index: 8676823 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8890. Min Range: -3.8890
Max Act: 3.6701. Min Act: -0.1700
Data Index: 2247489 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8890. Min Range: -3.8890
Max Act: 3.6857. Min Act: -0.1700
Data Index: 4587062 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8890. Min Range: -3.8890
Max Act: 3.6701. Min Act: -0.1700
Data Index: 3818255 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8890. Min Range: -3.8890
Max Act: 3.6388. Min Act: -0.1700
Data Index: 7482436 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8890. Min Range: -3.8890
Max Act: 3.6388. Min Act: -0.1700
Data Index: 6690503 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8890. Min Range: -3.8890
Max Act: 3.6388. Min Act: -0.1700
Data Index: 6504551 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8890. Min Range: -3.8890
Max Act: 3.6544. Min Act: -0.1700
Data Index: 6417585 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8890. Min Range: -3.8890
Max Act: 3.6232. Min Act: -0.1700
Data Index: 1403027 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8890. Min Range: -3.8890
Max Act: 3.6232. Min Act: -0.1700
Data Index: 3624034 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8890. Min Range: -3.8890
Max Act: 3.6388. Min Act: -0.1700
Data Index: 5114822 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8890. Min Range: -3.8890
Max Act: 3.6075. Min Act: -0.1700
Data Index: 5925738 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #19