Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2775 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3595. Min Range: -10.3595
Max Act: 10.3595. Min Act: -0.1700
Data Index: 3036063 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3595. Min Range: -10.3595
Max Act: 10.0470. Min Act: -0.1700
Data Index: 135215 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3595. Min Range: -10.3595
Max Act: 10.0470. Min Act: -0.1700
Data Index: 4668012 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3595. Min Range: -10.3595
Max Act: 9.9220. Min Act: -0.1700
Data Index: 1722833 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3595. Min Range: -10.3595
Max Act: 9.8595. Min Act: -0.1700
Data Index: 8675002 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3595. Min Range: -10.3595
Max Act: 9.8595. Min Act: -0.1700
Data Index: 3064345 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3595. Min Range: -10.3595
Max Act: 9.7970. Min Act: -0.1700
Data Index: 6225982 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3595. Min Range: -10.3595
Max Act: 9.7345. Min Act: -0.1700
Data Index: 552475 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3595. Min Range: -10.3595
Max Act: 9.6720. Min Act: -0.1700
Data Index: 1556315 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3595. Min Range: -10.3595
Max Act: 9.7345. Min Act: -0.1700
Data Index: 8796191 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3595. Min Range: -10.3595
Max Act: 9.7345. Min Act: -0.1700
Data Index: 2793026 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3595. Min Range: -10.3595
Max Act: 9.7345. Min Act: -0.1700
Data Index: 3740054 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3595. Min Range: -10.3595
Max Act: 9.7345. Min Act: -0.1700
Data Index: 5739377 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3595. Min Range: -10.3595
Max Act: 9.6720. Min Act: -0.1700
Data Index: 1678740 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3595. Min Range: -10.3595
Max Act: 9.6095. Min Act: -0.1700
Data Index: 3139740 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3595. Min Range: -10.3595
Max Act: 9.6095. Min Act: -0.1700
Data Index: 6840056 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3595. Min Range: -10.3595
Max Act: 9.6095. Min Act: -0.1700
Data Index: 8308181 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3595. Min Range: -10.3595
Max Act: 9.5470. Min Act: -0.1700
Data Index: 3510477 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3595. Min Range: -10.3595
Max Act: 9.5470. Min Act: -0.1700
Data Index: 2696852 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3595. Min Range: -10.3595
Max Act: 9.5470. Min Act: -0.1700
Data Index: 172853 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #19