Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2688 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.0840. Min Range: -3.0840
Max Act: 3.0840. Min Act: -0.1700
Data Index: 7956090 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0840. Min Range: -3.0840
Max Act: 3.0682. Min Act: -0.1700
Data Index: 2180325 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0840. Min Range: -3.0840
Max Act: 3.0524. Min Act: -0.1700
Data Index: 5267274 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0840. Min Range: -3.0840
Max Act: 2.9576. Min Act: -0.1700
Data Index: 3338195 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0840. Min Range: -3.0840
Max Act: 2.9734. Min Act: -0.1700
Data Index: 3380252 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0840. Min Range: -3.0840
Max Act: 2.9576. Min Act: -0.1700
Data Index: 5417190 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0840. Min Range: -3.0840
Max Act: 2.9418. Min Act: -0.1700
Data Index: 2931037 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0840. Min Range: -3.0840
Max Act: 2.9418. Min Act: -0.1700
Data Index: 2817613 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0840. Min Range: -3.0840
Max Act: 2.9418. Min Act: -0.1700
Data Index: 5045916 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0840. Min Range: -3.0840
Max Act: 2.9418. Min Act: -0.1700
Data Index: 4987528 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0840. Min Range: -3.0840
Max Act: 2.9260. Min Act: -0.1700
Data Index: 2490743 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0840. Min Range: -3.0840
Max Act: 2.9418. Min Act: -0.1700
Data Index: 4889391 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0840. Min Range: -3.0840
Max Act: 2.9101. Min Act: -0.1700
Data Index: 8354020 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0840. Min Range: -3.0840
Max Act: 2.9101. Min Act: -0.1700
Data Index: 1245771 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0840. Min Range: -3.0840
Max Act: 2.9101. Min Act: -0.1700
Data Index: 7085890 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0840. Min Range: -3.0840
Max Act: 2.9101. Min Act: -0.1700
Data Index: 43366 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0840. Min Range: -3.0840
Max Act: 2.9101. Min Act: -0.1700
Data Index: 653155 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0840. Min Range: -3.0840
Max Act: 2.8943. Min Act: -0.1700
Data Index: 2302336 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0840. Min Range: -3.0840
Max Act: 2.9101. Min Act: -0.1700
Data Index: 2061841 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0840. Min Range: -3.0840
Max Act: 2.8943. Min Act: -0.1700
Data Index: 5315964 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #19