Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3003 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1541. Min Range: -9.1541
Max Act: 9.1541. Min Act: -0.1700
Data Index: 7464320 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1541. Min Range: -9.1541
Max Act: 9.1541. Min Act: -0.1700
Data Index: 7197984 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1541. Min Range: -9.1541
Max Act: 9.0291. Min Act: -0.1700
Data Index: 8546239 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1541. Min Range: -9.1541
Max Act: 9.0291. Min Act: -0.1700
Data Index: 5907498 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1541. Min Range: -9.1541
Max Act: 8.9666. Min Act: -0.1700
Data Index: 10022 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1541. Min Range: -9.1541
Max Act: 8.9041. Min Act: -0.1700
Data Index: 7272706 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1541. Min Range: -9.1541
Max Act: 8.8416. Min Act: -0.1699
Data Index: 5596642 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1541. Min Range: -9.1541
Max Act: 8.8416. Min Act: -0.1700
Data Index: 1550607 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1541. Min Range: -9.1541
Max Act: 8.7791. Min Act: -0.1700
Data Index: 3846835 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1541. Min Range: -9.1541
Max Act: 8.7791. Min Act: -0.1700
Data Index: 373978 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1541. Min Range: -9.1541
Max Act: 8.6541. Min Act: -0.1700
Data Index: 5150073 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1541. Min Range: -9.1541
Max Act: 8.6541. Min Act: -0.1700
Data Index: 1472724 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1541. Min Range: -9.1541
Max Act: 8.6541. Min Act: -0.1700
Data Index: 4498762 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1541. Min Range: -9.1541
Max Act: 8.6541. Min Act: -0.1700
Data Index: 8157314 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1541. Min Range: -9.1541
Max Act: 8.6541. Min Act: -0.1700
Data Index: 5499467 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1541. Min Range: -9.1541
Max Act: 8.6541. Min Act: -0.1700
Data Index: 796035 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1541. Min Range: -9.1541
Max Act: 8.6541. Min Act: -0.1700
Data Index: 3543495 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1541. Min Range: -9.1541
Max Act: 8.5916. Min Act: -0.1700
Data Index: 7074154 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1541. Min Range: -9.1541
Max Act: 8.5916. Min Act: -0.1700
Data Index: 5487722 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1541. Min Range: -9.1541
Max Act: 8.5916. Min Act: -0.1700
Data Index: 7906618 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #19