Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 939 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.2991. Min Range: -5.2991
Max Act: 5.2991. Min Act: -0.1700
Data Index: 6063586 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2991. Min Range: -5.2991
Max Act: 5.2053. Min Act: -0.1700
Data Index: 3582251 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2991. Min Range: -5.2991
Max Act: 5.2053. Min Act: -0.1700
Data Index: 7288028 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2991. Min Range: -5.2991
Max Act: 5.1428. Min Act: -0.1700
Data Index: 6699566 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2991. Min Range: -5.2991
Max Act: 5.0803. Min Act: -0.1700
Data Index: 3743427 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2991. Min Range: -5.2991
Max Act: 5.0491. Min Act: -0.1700
Data Index: 3168454 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2991. Min Range: -5.2991
Max Act: 4.9866. Min Act: -0.1700
Data Index: 7708273 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2991. Min Range: -5.2991
Max Act: 4.9866. Min Act: -0.1700
Data Index: 4535100 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2991. Min Range: -5.2991
Max Act: 4.9866. Min Act: -0.1700
Data Index: 2100320 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2991. Min Range: -5.2991
Max Act: 4.9553. Min Act: -0.1700
Data Index: 4876531 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2991. Min Range: -5.2991
Max Act: 4.9553. Min Act: -0.1700
Data Index: 5979080 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2991. Min Range: -5.2991
Max Act: 4.9241. Min Act: -0.1700
Data Index: 3332955 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2991. Min Range: -5.2991
Max Act: 4.9866. Min Act: -0.1700
Data Index: 41824 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2991. Min Range: -5.2991
Max Act: 4.9553. Min Act: -0.1700
Data Index: 3229307 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2991. Min Range: -5.2991
Max Act: 4.9553. Min Act: -0.1700
Data Index: 7561766 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2991. Min Range: -5.2991
Max Act: 4.8928. Min Act: -0.1700
Data Index: 1280245 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2991. Min Range: -5.2991
Max Act: 4.9553. Min Act: -0.1700
Data Index: 1645776 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2991. Min Range: -5.2991
Max Act: 4.9241. Min Act: -0.1700
Data Index: 919091 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2991. Min Range: -5.2991
Max Act: 4.8928. Min Act: -0.1700
Data Index: 2778386 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2991. Min Range: -5.2991
Max Act: 4.9241. Min Act: -0.1700
Data Index: 1020761 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #19