Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6386 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4485. Min Range: -4.4485
Max Act: 4.4485. Min Act: -0.1700
Data Index: 6933436 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4485. Min Range: -4.4485
Max Act: 4.3860. Min Act: -0.1700
Data Index: 8728271 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4485. Min Range: -4.4485
Max Act: 4.3860. Min Act: -0.1700
Data Index: 2133809 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4485. Min Range: -4.4485
Max Act: 4.3860. Min Act: -0.1700
Data Index: 4113614 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4485. Min Range: -4.4485
Max Act: 4.3547. Min Act: -0.1700
Data Index: 6752220 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4485. Min Range: -4.4485
Max Act: 4.3235. Min Act: -0.1700
Data Index: 7987882 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4485. Min Range: -4.4485
Max Act: 4.3235. Min Act: -0.1700
Data Index: 7880976 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4485. Min Range: -4.4485
Max Act: 4.3235. Min Act: -0.1700
Data Index: 8365665 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4485. Min Range: -4.4485
Max Act: 4.3235. Min Act: -0.1700
Data Index: 5989779 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4485. Min Range: -4.4485
Max Act: 4.2922. Min Act: -0.1700
Data Index: 3041828 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4485. Min Range: -4.4485
Max Act: 4.2922. Min Act: -0.1700
Data Index: 6690903 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4485. Min Range: -4.4485
Max Act: 4.2922. Min Act: -0.1700
Data Index: 7514651 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4485. Min Range: -4.4485
Max Act: 4.2610. Min Act: -0.1700
Data Index: 6033562 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4485. Min Range: -4.4485
Max Act: 4.2610. Min Act: -0.1700
Data Index: 5699775 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4485. Min Range: -4.4485
Max Act: 4.2610. Min Act: -0.1700
Data Index: 4046835 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4485. Min Range: -4.4485
Max Act: 4.2610. Min Act: -0.1700
Data Index: 5028330 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4485. Min Range: -4.4485
Max Act: 4.2610. Min Act: -0.1700
Data Index: 3676001 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4485. Min Range: -4.4485
Max Act: 4.2610. Min Act: -0.1700
Data Index: 7913412 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4485. Min Range: -4.4485
Max Act: 4.2610. Min Act: -0.1700
Data Index: 7911245 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4485. Min Range: -4.4485
Max Act: 4.2297. Min Act: -0.1700
Data Index: 3254888 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #19