Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3815 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4835. Min Range: -9.4835
Max Act: 9.4835. Min Act: -0.1700
Data Index: 2929718 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4835. Min Range: -9.4835
Max Act: 9.3585. Min Act: -0.1700
Data Index: 508852 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4835. Min Range: -9.4835
Max Act: 9.2960. Min Act: -0.1700
Data Index: 2687223 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4835. Min Range: -9.4835
Max Act: 8.9835. Min Act: -0.1700
Data Index: 3583392 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4835. Min Range: -9.4835
Max Act: 8.8585. Min Act: -0.1700
Data Index: 8441134 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4835. Min Range: -9.4835
Max Act: 8.7960. Min Act: -0.1700
Data Index: 6455155 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4835. Min Range: -9.4835
Max Act: 8.7960. Min Act: -0.1700
Data Index: 6450827 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4835. Min Range: -9.4835
Max Act: 8.7960. Min Act: -0.1700
Data Index: 8119097 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4835. Min Range: -9.4835
Max Act: 8.7960. Min Act: -0.1700
Data Index: 6355485 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4835. Min Range: -9.4835
Max Act: 8.7960. Min Act: -0.1700
Data Index: 7208665 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4835. Min Range: -9.4835
Max Act: 8.7335. Min Act: -0.1700
Data Index: 320216 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4835. Min Range: -9.4835
Max Act: 8.7335. Min Act: -0.1700
Data Index: 3421617 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4835. Min Range: -9.4835
Max Act: 8.7335. Min Act: -0.1700
Data Index: 5163876 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4835. Min Range: -9.4835
Max Act: 8.7335. Min Act: -0.1700
Data Index: 1650685 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4835. Min Range: -9.4835
Max Act: 8.6710. Min Act: -0.1700
Data Index: 4122004 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4835. Min Range: -9.4835
Max Act: 8.7335. Min Act: -0.1700
Data Index: 1385517 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4835. Min Range: -9.4835
Max Act: 8.6085. Min Act: -0.1700
Data Index: 4382471 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4835. Min Range: -9.4835
Max Act: 8.6085. Min Act: -0.1700
Data Index: 4090 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4835. Min Range: -9.4835
Max Act: 8.6085. Min Act: -0.1700
Data Index: 2301862 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4835. Min Range: -9.4835
Max Act: 8.6085. Min Act: -0.1700
Data Index: 7479997 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #19