Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3206 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3170. Min Range: -8.3170
Max Act: 8.3170. Min Act: -0.1700
Data Index: 7898327 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3170. Min Range: -8.3170
Max Act: 8.1295. Min Act: -0.1700
Data Index: 3053808 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3170. Min Range: -8.3170
Max Act: 8.1295. Min Act: -0.1700
Data Index: 1956859 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3170. Min Range: -8.3170
Max Act: 8.0670. Min Act: -0.1700
Data Index: 4401057 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3170. Min Range: -8.3170
Max Act: 7.9108. Min Act: -0.1700
Data Index: 3582920 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3170. Min Range: -8.3170
Max Act: 7.8795. Min Act: -0.1700
Data Index: 2417983 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3170. Min Range: -8.3170
Max Act: 7.8795. Min Act: -0.1700
Data Index: 8359964 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3170. Min Range: -8.3170
Max Act: 7.8483. Min Act: -0.1700
Data Index: 3909394 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3170. Min Range: -8.3170
Max Act: 7.8795. Min Act: -0.1700
Data Index: 7988436 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3170. Min Range: -8.3170
Max Act: 7.7233. Min Act: -0.1700
Data Index: 2781829 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3170. Min Range: -8.3170
Max Act: 7.7233. Min Act: -0.1700
Data Index: 8070070 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3170. Min Range: -8.3170
Max Act: 7.7233. Min Act: -0.1700
Data Index: 5250292 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3170. Min Range: -8.3170
Max Act: 7.7233. Min Act: -0.1700
Data Index: 7876377 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3170. Min Range: -8.3170
Max Act: 7.7233. Min Act: -0.1700
Data Index: 1638499 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3170. Min Range: -8.3170
Max Act: 7.6920. Min Act: -0.1700
Data Index: 4001958 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3170. Min Range: -8.3170
Max Act: 7.6920. Min Act: -0.1700
Data Index: 161384 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3170. Min Range: -8.3170
Max Act: 7.6608. Min Act: -0.1700
Data Index: 8170752 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3170. Min Range: -8.3170
Max Act: 7.6608. Min Act: -0.1700
Data Index: 6344933 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3170. Min Range: -8.3170
Max Act: 7.6295. Min Act: -0.1700
Data Index: 2965898 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3170. Min Range: -8.3170
Max Act: 7.6295. Min Act: -0.1700
Data Index: 1971824 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #19