Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3326 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4203. Min Range: -3.4203
Max Act: 3.4203. Min Act: -0.1700
Data Index: 7106306 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4203. Min Range: -3.4203
Max Act: 3.3576. Min Act: -0.1700
Data Index: 886436 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4203. Min Range: -3.4203
Max Act: 3.3262. Min Act: -0.1700
Data Index: 1316383 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4203. Min Range: -3.4203
Max Act: 3.3105. Min Act: -0.1700
Data Index: 8104963 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4203. Min Range: -3.4203
Max Act: 3.3105. Min Act: -0.1700
Data Index: 5284847 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4203. Min Range: -3.4203
Max Act: 3.2948. Min Act: -0.1700
Data Index: 7622125 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4203. Min Range: -3.4203
Max Act: 3.2948. Min Act: -0.1700
Data Index: 6063295 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4203. Min Range: -3.4203
Max Act: 3.2791. Min Act: -0.1700
Data Index: 2228396 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4203. Min Range: -3.4203
Max Act: 3.2791. Min Act: -0.1700
Data Index: 6663303 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4203. Min Range: -3.4203
Max Act: 3.2634. Min Act: -0.1700
Data Index: 5183410 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4203. Min Range: -3.4203
Max Act: 3.2791. Min Act: -0.1700
Data Index: 4908040 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4203. Min Range: -3.4203
Max Act: 3.2477. Min Act: -0.1700
Data Index: 1184494 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4203. Min Range: -3.4203
Max Act: 3.2477. Min Act: -0.1700
Data Index: 8158515 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4203. Min Range: -3.4203
Max Act: 3.2477. Min Act: -0.1700
Data Index: 5242282 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4203. Min Range: -3.4203
Max Act: 3.2320. Min Act: -0.1700
Data Index: 1898166 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4203. Min Range: -3.4203
Max Act: 3.2320. Min Act: -0.1700
Data Index: 2937201 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4203. Min Range: -3.4203
Max Act: 3.2320. Min Act: -0.1700
Data Index: 3452401 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4203. Min Range: -3.4203
Max Act: 3.2320. Min Act: -0.1700
Data Index: 5470338 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4203. Min Range: -3.4203
Max Act: 3.2320. Min Act: -0.1700
Data Index: 1092518 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4203. Min Range: -3.4203
Max Act: 3.2320. Min Act: -0.1700
Data Index: 4045765 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #19