Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3347 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.8508. Min Range: -2.8508
Max Act: 2.8508. Min Act: -0.1700
Data Index: 50528 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8508. Min Range: -2.8508
Max Act: 2.8190. Min Act: -0.1699
Data Index: 6133782 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8508. Min Range: -2.8508
Max Act: 2.8030. Min Act: -0.1700
Data Index: 206687 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8508. Min Range: -2.8508
Max Act: 2.8349. Min Act: -0.1700
Data Index: 6416723 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8508. Min Range: -2.8508
Max Act: 2.8349. Min Act: -0.1700
Data Index: 6941235 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8508. Min Range: -2.8508
Max Act: 2.8030. Min Act: -0.1700
Data Index: 536216 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8508. Min Range: -2.8508
Max Act: 2.7871. Min Act: -0.1692
Data Index: 3052673 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8508. Min Range: -2.8508
Max Act: 2.7871. Min Act: -0.1700
Data Index: 8114407 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8508. Min Range: -2.8508
Max Act: 2.7871. Min Act: -0.1700
Data Index: 900288 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8508. Min Range: -2.8508
Max Act: 2.7871. Min Act: -0.1700
Data Index: 8097498 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8508. Min Range: -2.8508
Max Act: 2.7871. Min Act: -0.1700
Data Index: 8030893 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8508. Min Range: -2.8508
Max Act: 2.7871. Min Act: -0.1700
Data Index: 5923365 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8508. Min Range: -2.8508
Max Act: 2.7871. Min Act: -0.1700
Data Index: 2588221 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8508. Min Range: -2.8508
Max Act: 2.7871. Min Act: -0.1700
Data Index: 7526409 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8508. Min Range: -2.8508
Max Act: 2.7712. Min Act: -0.1700
Data Index: 7335170 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8508. Min Range: -2.8508
Max Act: 2.7552. Min Act: -0.1700
Data Index: 5814958 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8508. Min Range: -2.8508
Max Act: 2.7552. Min Act: -0.1700
Data Index: 4596720 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8508. Min Range: -2.8508
Max Act: 2.7552. Min Act: -0.1700
Data Index: 1003132 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8508. Min Range: -2.8508
Max Act: 2.7712. Min Act: -0.1700
Data Index: 7300552 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8508. Min Range: -2.8508
Max Act: 2.7393. Min Act: -0.1700
Data Index: 3160940 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #19