Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1005 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.9482. Min Range: -2.9482
Max Act: 2.9482. Min Act: -0.1105
Data Index: 7093569 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.9482. Min Range: -2.9482
Max Act: 2.9165. Min Act: -0.0365
Data Index: 6707039 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.9482. Min Range: -2.9482
Max Act: 2.9165. Min Act: -0.1320
Data Index: 6707061 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.9482. Min Range: -2.9482
Max Act: 2.9006. Min Act: -0.1189
Data Index: 7091192 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.9482. Min Range: -2.9482
Max Act: 2.8848. Min Act: -0.1418
Data Index: 6761402 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.9482. Min Range: -2.9482
Max Act: 2.8848. Min Act: -0.0686
Data Index: 6707042 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.9482. Min Range: -2.9482
Max Act: 2.9006. Min Act: -0.1446
Data Index: 6862608 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.9482. Min Range: -2.9482
Max Act: 2.9006. Min Act: -0.1700
Data Index: 3504847 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.9482. Min Range: -2.9482
Max Act: 2.8848. Min Act: -0.0052
Data Index: 6707040 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.9482. Min Range: -2.9482
Max Act: 2.8530. Min Act: -0.0289
Data Index: 6707044 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.9482. Min Range: -2.9482
Max Act: 2.8212. Min Act: -0.1670
Data Index: 4780495 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.9482. Min Range: -2.9482
Max Act: 2.8371. Min Act: -0.1697
Data Index: 8644545 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.9482. Min Range: -2.9482
Max Act: 2.8053. Min Act: -0.1645
Data Index: 6457227 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.9482. Min Range: -2.9482
Max Act: 2.8053. Min Act: -0.1472
Data Index: 2335542 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.9482. Min Range: -2.9482
Max Act: 2.8053. Min Act: -0.0260
Data Index: 6707033 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.9482. Min Range: -2.9482
Max Act: 2.8053. Min Act: -0.0995
Data Index: 390865 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.9482. Min Range: -2.9482
Max Act: 2.8053. Min Act: -0.0000
Data Index: 6707047 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.9482. Min Range: -2.9482
Max Act: 2.7894. Min Act: -0.0709
Data Index: 6707035 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.9482. Min Range: -2.9482
Max Act: 2.8053. Min Act: -0.1116
Data Index: 1464259 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.9482. Min Range: -2.9482
Max Act: 2.7894. Min Act: -0.0355
Data Index: 6707051 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #19