Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5084 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.6933. Min Range: -4.6933
Max Act: 4.6933. Min Act: -0.1700
Data Index: 4426601 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6933. Min Range: -4.6933
Max Act: 4.6621. Min Act: -0.1700
Data Index: 2118166 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6933. Min Range: -4.6933
Max Act: 4.6621. Min Act: -0.1700
Data Index: 2158194 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6933. Min Range: -4.6933
Max Act: 4.6308. Min Act: -0.1700
Data Index: 1046827 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6933. Min Range: -4.6933
Max Act: 4.5996. Min Act: -0.1700
Data Index: 2106702 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6933. Min Range: -4.6933
Max Act: 4.6308. Min Act: -0.1700
Data Index: 2158193 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6933. Min Range: -4.6933
Max Act: 4.5683. Min Act: -0.1700
Data Index: 1952459 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6933. Min Range: -4.6933
Max Act: 4.5683. Min Act: -0.1700
Data Index: 8613439 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6933. Min Range: -4.6933
Max Act: 4.5683. Min Act: -0.1700
Data Index: 1444966 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6933. Min Range: -4.6933
Max Act: 4.5371. Min Act: -0.1700
Data Index: 79114 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6933. Min Range: -4.6933
Max Act: 4.5371. Min Act: -0.1700
Data Index: 3031623 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6933. Min Range: -4.6933
Max Act: 4.5058. Min Act: -0.1700
Data Index: 4550322 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6933. Min Range: -4.6933
Max Act: 4.5058. Min Act: -0.1700
Data Index: 1653738 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6933. Min Range: -4.6933
Max Act: 4.5058. Min Act: -0.1700
Data Index: 8259487 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6933. Min Range: -4.6933
Max Act: 4.5058. Min Act: -0.1700
Data Index: 3890545 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6933. Min Range: -4.6933
Max Act: 4.4746. Min Act: -0.1700
Data Index: 2553329 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6933. Min Range: -4.6933
Max Act: 4.4746. Min Act: -0.1700
Data Index: 8149972 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6933. Min Range: -4.6933
Max Act: 4.4746. Min Act: -0.1700
Data Index: 4801081 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6933. Min Range: -4.6933
Max Act: 4.4746. Min Act: -0.1700
Data Index: 4399578 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6933. Min Range: -4.6933
Max Act: 4.4433. Min Act: -0.1700
Data Index: 1522830 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19