Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3042 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1365. Min Range: -7.1365
Max Act: 7.1365. Min Act: -0.1700
Data Index: 1154814 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1365. Min Range: -7.1365
Max Act: 7.0115. Min Act: -0.1700
Data Index: 3327983 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1365. Min Range: -7.1365
Max Act: 6.9178. Min Act: -0.1700
Data Index: 286040 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1365. Min Range: -7.1365
Max Act: 6.8240. Min Act: -0.1700
Data Index: 5979533 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1365. Min Range: -7.1365
Max Act: 6.8240. Min Act: -0.1700
Data Index: 7229213 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1365. Min Range: -7.1365
Max Act: 6.7928. Min Act: -0.1700
Data Index: 4412381 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1365. Min Range: -7.1365
Max Act: 6.7615. Min Act: -0.1700
Data Index: 2093990 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1365. Min Range: -7.1365
Max Act: 6.7615. Min Act: -0.1700
Data Index: 6771736 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1365. Min Range: -7.1365
Max Act: 6.7615. Min Act: -0.1700
Data Index: 7101112 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1365. Min Range: -7.1365
Max Act: 6.6365. Min Act: -0.1700
Data Index: 226250 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1365. Min Range: -7.1365
Max Act: 6.6365. Min Act: -0.1700
Data Index: 431519 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1365. Min Range: -7.1365
Max Act: 6.6053. Min Act: -0.1700
Data Index: 6544614 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1365. Min Range: -7.1365
Max Act: 6.6365. Min Act: -0.1700
Data Index: 4272436 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1365. Min Range: -7.1365
Max Act: 6.6053. Min Act: -0.1700
Data Index: 4445641 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1365. Min Range: -7.1365
Max Act: 6.5428. Min Act: -0.1700
Data Index: 6293127 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1365. Min Range: -7.1365
Max Act: 6.5115. Min Act: -0.1700
Data Index: 4095067 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1365. Min Range: -7.1365
Max Act: 6.5115. Min Act: -0.1700
Data Index: 2693671 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1365. Min Range: -7.1365
Max Act: 6.5115. Min Act: -0.1700
Data Index: 7256752 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1365. Min Range: -7.1365
Max Act: 6.4803. Min Act: -0.1700
Data Index: 6054501 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1365. Min Range: -7.1365
Max Act: 6.4803. Min Act: -0.1700
Data Index: 2150861 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #19