Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5093 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2062. Min Range: -4.2062
Max Act: 4.2062. Min Act: -0.1700
Data Index: 3032062 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2062. Min Range: -4.2062
Max Act: 3.9561. Min Act: -0.1700
Data Index: 819375 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2062. Min Range: -4.2062
Max Act: 3.9249. Min Act: -0.1700
Data Index: 683033 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2062. Min Range: -4.2062
Max Act: 3.9405. Min Act: -0.1700
Data Index: 7746013 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2062. Min Range: -4.2062
Max Act: 3.9249. Min Act: -0.1700
Data Index: 5837128 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2062. Min Range: -4.2062
Max Act: 3.8936. Min Act: -0.1700
Data Index: 4460211 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2062. Min Range: -4.2062
Max Act: 3.9092. Min Act: -0.1700
Data Index: 8762972 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2062. Min Range: -4.2062
Max Act: 3.8623. Min Act: -0.1700
Data Index: 7654711 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2062. Min Range: -4.2062
Max Act: 3.8467. Min Act: -0.1700
Data Index: 3958839 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2062. Min Range: -4.2062
Max Act: 3.8467. Min Act: -0.1700
Data Index: 5997502 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2062. Min Range: -4.2062
Max Act: 3.8311. Min Act: -0.1700
Data Index: 3884152 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2062. Min Range: -4.2062
Max Act: 3.8311. Min Act: -0.1700
Data Index: 7649925 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2062. Min Range: -4.2062
Max Act: 3.8311. Min Act: -0.1700
Data Index: 46711 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2062. Min Range: -4.2062
Max Act: 3.8154. Min Act: -0.1700
Data Index: 1172321 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2062. Min Range: -4.2062
Max Act: 3.7998. Min Act: -0.1700
Data Index: 6011290 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2062. Min Range: -4.2062
Max Act: 3.7998. Min Act: -0.1700
Data Index: 8274767 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2062. Min Range: -4.2062
Max Act: 3.7998. Min Act: -0.1700
Data Index: 4954915 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2062. Min Range: -4.2062
Max Act: 3.7841. Min Act: -0.1700
Data Index: 8790303 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2062. Min Range: -4.2062
Max Act: 3.7998. Min Act: -0.1700
Data Index: 6499399 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2062. Min Range: -4.2062
Max Act: 3.7841. Min Act: -0.1700
Data Index: 8366283 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #19