Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2354 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9240. Min Range: -4.9240
Max Act: 4.9240. Min Act: -0.1700
Data Index: 2062870 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9240. Min Range: -4.9240
Max Act: 4.8927. Min Act: -0.1700
Data Index: 2457830 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9240. Min Range: -4.9240
Max Act: 4.8615. Min Act: -0.1700
Data Index: 7898353 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9240. Min Range: -4.9240
Max Act: 4.8927. Min Act: -0.1700
Data Index: 1751712 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9240. Min Range: -4.9240
Max Act: 4.8615. Min Act: -0.1700
Data Index: 2602250 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9240. Min Range: -4.9240
Max Act: 4.8615. Min Act: -0.1700
Data Index: 1040073 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9240. Min Range: -4.9240
Max Act: 4.8302. Min Act: -0.1700
Data Index: 5056218 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9240. Min Range: -4.9240
Max Act: 4.8615. Min Act: -0.1700
Data Index: 7277133 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9240. Min Range: -4.9240
Max Act: 4.7677. Min Act: -0.1700
Data Index: 7836606 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9240. Min Range: -4.9240
Max Act: 4.7990. Min Act: -0.1700
Data Index: 8715174 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9240. Min Range: -4.9240
Max Act: 4.7990. Min Act: -0.1700
Data Index: 5056234 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9240. Min Range: -4.9240
Max Act: 4.7677. Min Act: -0.1700
Data Index: 5219341 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9240. Min Range: -4.9240
Max Act: 4.7677. Min Act: -0.1700
Data Index: 2078527 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9240. Min Range: -4.9240
Max Act: 4.7677. Min Act: -0.1700
Data Index: 3664680 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9240. Min Range: -4.9240
Max Act: 4.7990. Min Act: -0.1700
Data Index: 5956733 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9240. Min Range: -4.9240
Max Act: 4.7677. Min Act: -0.1699
Data Index: 2287467 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9240. Min Range: -4.9240
Max Act: 4.7677. Min Act: -0.1700
Data Index: 1767749 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9240. Min Range: -4.9240
Max Act: 4.7677. Min Act: -0.1700
Data Index: 4957244 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9240. Min Range: -4.9240
Max Act: 4.7365. Min Act: -0.1700
Data Index: 3546294 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9240. Min Range: -4.9240
Max Act: 4.7365. Min Act: -0.1700
Data Index: 6450768 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #19