Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1971 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3835. Min Range: -8.3835
Max Act: 8.3835. Min Act: -0.1700
Data Index: 7322568 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3835. Min Range: -8.3835
Max Act: 8.2585. Min Act: -0.1700
Data Index: 4531568 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3835. Min Range: -8.3835
Max Act: 8.2273. Min Act: -0.1700
Data Index: 142685 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3835. Min Range: -8.3835
Max Act: 8.1648. Min Act: -0.1700
Data Index: 1562208 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3835. Min Range: -8.3835
Max Act: 8.1648. Min Act: -0.1700
Data Index: 276554 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3835. Min Range: -8.3835
Max Act: 8.1648. Min Act: -0.1700
Data Index: 1384359 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3835. Min Range: -8.3835
Max Act: 8.1648. Min Act: -0.1700
Data Index: 8020406 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3835. Min Range: -8.3835
Max Act: 8.1335. Min Act: -0.1700
Data Index: 8000134 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3835. Min Range: -8.3835
Max Act: 8.1023. Min Act: -0.1700
Data Index: 1492531 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3835. Min Range: -8.3835
Max Act: 8.0710. Min Act: -0.1700
Data Index: 7040949 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3835. Min Range: -8.3835
Max Act: 8.0085. Min Act: -0.1700
Data Index: 1764487 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3835. Min Range: -8.3835
Max Act: 7.9773. Min Act: -0.1700
Data Index: 524994 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3835. Min Range: -8.3835
Max Act: 7.9148. Min Act: -0.1700
Data Index: 8130580 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3835. Min Range: -8.3835
Max Act: 7.9148. Min Act: -0.1700
Data Index: 2351440 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3835. Min Range: -8.3835
Max Act: 7.9148. Min Act: -0.1700
Data Index: 6494656 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3835. Min Range: -8.3835
Max Act: 7.8210. Min Act: -0.1700
Data Index: 6439136 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3835. Min Range: -8.3835
Max Act: 7.8210. Min Act: -0.1700
Data Index: 8487907 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3835. Min Range: -8.3835
Max Act: 7.8210. Min Act: -0.1700
Data Index: 367238 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3835. Min Range: -8.3835
Max Act: 7.8210. Min Act: -0.1700
Data Index: 7764273 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3835. Min Range: -8.3835
Max Act: 7.7898. Min Act: -0.1700
Data Index: 5036574 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #19