Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5107 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.8491. Min Range: -4.8491
Max Act: 4.8491. Min Act: -0.1700
Data Index: 3214231 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8491. Min Range: -4.8491
Max Act: 4.7554. Min Act: -0.1700
Data Index: 7658414 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8491. Min Range: -4.8491
Max Act: 4.6616. Min Act: -0.1700
Data Index: 4851219 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8491. Min Range: -4.8491
Max Act: 4.6304. Min Act: -0.1700
Data Index: 3394743 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8491. Min Range: -4.8491
Max Act: 4.5991. Min Act: -0.1700
Data Index: 645470 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8491. Min Range: -4.8491
Max Act: 4.6304. Min Act: -0.1700
Data Index: 8183339 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8491. Min Range: -4.8491
Max Act: 4.5991. Min Act: -0.1700
Data Index: 3007286 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8491. Min Range: -4.8491
Max Act: 4.5679. Min Act: -0.1700
Data Index: 4840458 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8491. Min Range: -4.8491
Max Act: 4.5679. Min Act: -0.1700
Data Index: 8309331 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8491. Min Range: -4.8491
Max Act: 4.5679. Min Act: -0.1700
Data Index: 8159295 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8491. Min Range: -4.8491
Max Act: 4.5991. Min Act: -0.1700
Data Index: 1141972 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8491. Min Range: -4.8491
Max Act: 4.5679. Min Act: -0.1700
Data Index: 331661 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8491. Min Range: -4.8491
Max Act: 4.5366. Min Act: -0.1700
Data Index: 2737142 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8491. Min Range: -4.8491
Max Act: 4.5054. Min Act: -0.1700
Data Index: 7353550 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8491. Min Range: -4.8491
Max Act: 4.5366. Min Act: -0.1700
Data Index: 1434590 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8491. Min Range: -4.8491
Max Act: 4.5054. Min Act: -0.1700
Data Index: 1373585 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8491. Min Range: -4.8491
Max Act: 4.5054. Min Act: -0.1700
Data Index: 5678157 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8491. Min Range: -4.8491
Max Act: 4.5054. Min Act: -0.1700
Data Index: 2334511 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8491. Min Range: -4.8491
Max Act: 4.4741. Min Act: -0.1700
Data Index: 1125542 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8491. Min Range: -4.8491
Max Act: 4.5054. Min Act: -0.1700
Data Index: 1629080 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #19