Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2201 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7403. Min Range: -2.7403
Max Act: 2.7403. Min Act: -0.1700
Data Index: 8694271 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7403. Min Range: -2.7403
Max Act: 2.4829. Min Act: -0.1700
Data Index: 3018217 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7403. Min Range: -2.7403
Max Act: 2.4667. Min Act: -0.1700
Data Index: 6215937 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7403. Min Range: -2.7403
Max Act: 2.4341. Min Act: -0.1700
Data Index: 4806489 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7403. Min Range: -2.7403
Max Act: 2.4015. Min Act: -0.1700
Data Index: 6531668 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7403. Min Range: -2.7403
Max Act: 2.4179. Min Act: -0.1700
Data Index: 1667307 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7403. Min Range: -2.7403
Max Act: 2.4015. Min Act: -0.1700
Data Index: 2607850 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7403. Min Range: -2.7403
Max Act: 2.3689. Min Act: -0.1700
Data Index: 2022646 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7403. Min Range: -2.7403
Max Act: 2.4179. Min Act: -0.1700
Data Index: 3458786 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7403. Min Range: -2.7403
Max Act: 2.4015. Min Act: -0.1700
Data Index: 4714544 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7403. Min Range: -2.7403
Max Act: 2.3852. Min Act: -0.1700
Data Index: 1087845 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7403. Min Range: -2.7403
Max Act: 2.3033. Min Act: -0.1700
Data Index: 2090551 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7403. Min Range: -2.7403
Max Act: 2.2207. Min Act: -0.1700
Data Index: 4490748 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7403. Min Range: -2.7403
Max Act: 2.3361. Min Act: -0.1700
Data Index: 4494002 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7403. Min Range: -2.7403
Max Act: 2.3525. Min Act: -0.1700
Data Index: 545935 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7403. Min Range: -2.7403
Max Act: 2.3361. Min Act: -0.1700
Data Index: 2124525 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7403. Min Range: -2.7403
Max Act: 2.2868. Min Act: -0.1700
Data Index: 3406237 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7403. Min Range: -2.7403
Max Act: 2.2703. Min Act: -0.1700
Data Index: 4490754 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7403. Min Range: -2.7403
Max Act: 2.2868. Min Act: -0.1700
Data Index: 7131034 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7403. Min Range: -2.7403
Max Act: 2.3033. Min Act: -0.1700
Data Index: 1793403 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #19