Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 580 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.0895. Min Range: -4.0895
Max Act: 4.0895. Min Act: -0.1700
Data Index: 3522805 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0895. Min Range: -4.0895
Max Act: 3.9332. Min Act: -0.1700
Data Index: 6271237 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0895. Min Range: -4.0895
Max Act: 3.9019. Min Act: -0.1700
Data Index: 1999049 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0895. Min Range: -4.0895
Max Act: 3.8707. Min Act: -0.1700
Data Index: 659048 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0895. Min Range: -4.0895
Max Act: 3.8707. Min Act: -0.1700
Data Index: 3028420 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0895. Min Range: -4.0895
Max Act: 3.8394. Min Act: -0.1700
Data Index: 5663434 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0895. Min Range: -4.0895
Max Act: 3.8394. Min Act: -0.1700
Data Index: 6858990 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0895. Min Range: -4.0895
Max Act: 3.8081. Min Act: -0.1700
Data Index: 5119352 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0895. Min Range: -4.0895
Max Act: 3.8081. Min Act: -0.1700
Data Index: 2172165 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0895. Min Range: -4.0895
Max Act: 3.7768. Min Act: -0.1700
Data Index: 6611742 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0895. Min Range: -4.0895
Max Act: 3.7768. Min Act: -0.1700
Data Index: 7563075 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0895. Min Range: -4.0895
Max Act: 3.7768. Min Act: -0.1700
Data Index: 7030270 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0895. Min Range: -4.0895
Max Act: 3.7768. Min Act: -0.1700
Data Index: 7217865 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0895. Min Range: -4.0895
Max Act: 3.7456. Min Act: -0.1700
Data Index: 6300071 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0895. Min Range: -4.0895
Max Act: 3.7456. Min Act: -0.1700
Data Index: 6252139 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0895. Min Range: -4.0895
Max Act: 3.7143. Min Act: -0.1700
Data Index: 5482085 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0895. Min Range: -4.0895
Max Act: 3.7143. Min Act: -0.1700
Data Index: 4324768 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0895. Min Range: -4.0895
Max Act: 3.7143. Min Act: -0.1700
Data Index: 2347467 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0895. Min Range: -4.0895
Max Act: 3.6830. Min Act: -0.1700
Data Index: 4250056 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0895. Min Range: -4.0895
Max Act: 3.6830. Min Act: -0.1700
Data Index: 6968480 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #19