Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 515 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1651. Min Range: -6.1651
Max Act: 6.1651. Min Act: -0.1700
Data Index: 8146707 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1651. Min Range: -6.1651
Max Act: 6.1339. Min Act: -0.1700
Data Index: 6208875 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1651. Min Range: -6.1651
Max Act: 6.1339. Min Act: -0.1700
Data Index: 2735774 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1651. Min Range: -6.1651
Max Act: 5.9464. Min Act: -0.1700
Data Index: 2703528 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1651. Min Range: -6.1651
Max Act: 5.9464. Min Act: -0.1700
Data Index: 7977462 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1651. Min Range: -6.1651
Max Act: 5.8839. Min Act: -0.1700
Data Index: 282420 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1651. Min Range: -6.1651
Max Act: 5.8526. Min Act: -0.1700
Data Index: 6725715 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1651. Min Range: -6.1651
Max Act: 5.8526. Min Act: -0.1700
Data Index: 3636818 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1651. Min Range: -6.1651
Max Act: 5.8214. Min Act: -0.1700
Data Index: 2411679 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1651. Min Range: -6.1651
Max Act: 5.8214. Min Act: -0.1700
Data Index: 6343850 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1651. Min Range: -6.1651
Max Act: 5.8214. Min Act: -0.1700
Data Index: 5358661 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1651. Min Range: -6.1651
Max Act: 5.8526. Min Act: -0.1700
Data Index: 5875909 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1651. Min Range: -6.1651
Max Act: 5.7589. Min Act: -0.1700
Data Index: 4763388 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1651. Min Range: -6.1651
Max Act: 5.8214. Min Act: -0.1700
Data Index: 3940225 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1651. Min Range: -6.1651
Max Act: 5.7276. Min Act: -0.1700
Data Index: 1521023 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1651. Min Range: -6.1651
Max Act: 5.7276. Min Act: -0.1700
Data Index: 359946 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1651. Min Range: -6.1651
Max Act: 5.7589. Min Act: -0.1700
Data Index: 7258194 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1651. Min Range: -6.1651
Max Act: 5.6964. Min Act: -0.1700
Data Index: 521853 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1651. Min Range: -6.1651
Max Act: 5.6651. Min Act: -0.1700
Data Index: 8819709 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1651. Min Range: -6.1651
Max Act: 5.6651. Min Act: -0.1700
Data Index: 5002071 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #19