Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1641 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0336. Min Range: -5.0336
Max Act: 5.0336. Min Act: -0.1700
Data Index: 1244335 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0336. Min Range: -5.0336
Max Act: 5.0024. Min Act: -0.1700
Data Index: 2729187 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0336. Min Range: -5.0336
Max Act: 4.9399. Min Act: -0.1700
Data Index: 2252885 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0336. Min Range: -5.0336
Max Act: 4.9086. Min Act: -0.1700
Data Index: 2905959 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0336. Min Range: -5.0336
Max Act: 4.9086. Min Act: -0.1700
Data Index: 2252886 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0336. Min Range: -5.0336
Max Act: 4.8461. Min Act: -0.1700
Data Index: 384283 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0336. Min Range: -5.0336
Max Act: 4.8149. Min Act: -0.1700
Data Index: 6560047 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0336. Min Range: -5.0336
Max Act: 4.8149. Min Act: -0.1700
Data Index: 8311836 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0336. Min Range: -5.0336
Max Act: 4.7836. Min Act: -0.1700
Data Index: 1336453 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0336. Min Range: -5.0336
Max Act: 4.7836. Min Act: -0.1700
Data Index: 384284 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0336. Min Range: -5.0336
Max Act: 4.7836. Min Act: -0.1700
Data Index: 5790753 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0336. Min Range: -5.0336
Max Act: 4.7836. Min Act: -0.1700
Data Index: 3965194 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0336. Min Range: -5.0336
Max Act: 4.8149. Min Act: -0.1700
Data Index: 5079159 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0336. Min Range: -5.0336
Max Act: 4.7524. Min Act: -0.1700
Data Index: 4696266 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0336. Min Range: -5.0336
Max Act: 4.7524. Min Act: -0.1700
Data Index: 4116284 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0336. Min Range: -5.0336
Max Act: 4.7524. Min Act: -0.1700
Data Index: 4687058 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0336. Min Range: -5.0336
Max Act: 4.7836. Min Act: -0.1700
Data Index: 7700075 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0336. Min Range: -5.0336
Max Act: 4.7524. Min Act: -0.1700
Data Index: 3738937 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0336. Min Range: -5.0336
Max Act: 4.7524. Min Act: -0.1700
Data Index: 5680230 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0336. Min Range: -5.0336
Max Act: 4.6899. Min Act: -0.1700
Data Index: 1655985 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19