Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1977 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7385. Min Range: -5.7385
Max Act: 5.7385. Min Act: -0.1700
Data Index: 8468359 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7385. Min Range: -5.7385
Max Act: 5.6447. Min Act: -0.1700
Data Index: 4691698 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7385. Min Range: -5.7385
Max Act: 5.5822. Min Act: -0.1700
Data Index: 2933900 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7385. Min Range: -5.7385
Max Act: 5.5197. Min Act: -0.1700
Data Index: 7039886 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7385. Min Range: -5.7385
Max Act: 5.4260. Min Act: -0.1700
Data Index: 2744318 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7385. Min Range: -5.7385
Max Act: 5.4260. Min Act: -0.1700
Data Index: 1362084 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7385. Min Range: -5.7385
Max Act: 5.4260. Min Act: -0.1700
Data Index: 2439671 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7385. Min Range: -5.7385
Max Act: 5.3947. Min Act: -0.1700
Data Index: 2416129 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7385. Min Range: -5.7385
Max Act: 5.3635. Min Act: -0.1700
Data Index: 2417128 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7385. Min Range: -5.7385
Max Act: 5.3947. Min Act: -0.1700
Data Index: 832298 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7385. Min Range: -5.7385
Max Act: 5.2697. Min Act: -0.1700
Data Index: 8625695 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7385. Min Range: -5.7385
Max Act: 5.3010. Min Act: -0.1700
Data Index: 1266252 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7385. Min Range: -5.7385
Max Act: 5.3010. Min Act: -0.1700
Data Index: 6522722 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7385. Min Range: -5.7385
Max Act: 5.3010. Min Act: -0.1700
Data Index: 5788036 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7385. Min Range: -5.7385
Max Act: 5.2697. Min Act: -0.1700
Data Index: 2087662 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7385. Min Range: -5.7385
Max Act: 5.3010. Min Act: -0.1700
Data Index: 6970099 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7385. Min Range: -5.7385
Max Act: 5.2697. Min Act: -0.1700
Data Index: 2622824 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7385. Min Range: -5.7385
Max Act: 5.3010. Min Act: -0.1700
Data Index: 2417129 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7385. Min Range: -5.7385
Max Act: 5.2697. Min Act: -0.1700
Data Index: 5005161 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7385. Min Range: -5.7385
Max Act: 5.2385. Min Act: -0.1700
Data Index: 3872495 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #19