Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3805 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7723. Min Range: -8.7723
Max Act: 8.7723. Min Act: -0.1700
Data Index: 4709312 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7723. Min Range: -8.7723
Max Act: 8.5848. Min Act: -0.1700
Data Index: 4149076 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7723. Min Range: -8.7723
Max Act: 8.5848. Min Act: -0.1700
Data Index: 7073020 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7723. Min Range: -8.7723
Max Act: 8.5223. Min Act: -0.1700
Data Index: 3987043 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7723. Min Range: -8.7723
Max Act: 8.4598. Min Act: -0.1700
Data Index: 8371737 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7723. Min Range: -8.7723
Max Act: 8.3973. Min Act: -0.1700
Data Index: 1039503 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7723. Min Range: -8.7723
Max Act: 8.3348. Min Act: -0.1700
Data Index: 7674693 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7723. Min Range: -8.7723
Max Act: 8.3348. Min Act: -0.1700
Data Index: 5749296 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7723. Min Range: -8.7723
Max Act: 8.2723. Min Act: -0.1700
Data Index: 266775 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7723. Min Range: -8.7723
Max Act: 8.2723. Min Act: -0.1700
Data Index: 1691343 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7723. Min Range: -8.7723
Max Act: 8.2723. Min Act: -0.1700
Data Index: 8182068 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7723. Min Range: -8.7723
Max Act: 8.2723. Min Act: -0.1700
Data Index: 5453156 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7723. Min Range: -8.7723
Max Act: 8.2723. Min Act: -0.1700
Data Index: 4233433 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7723. Min Range: -8.7723
Max Act: 8.2723. Min Act: -0.1700
Data Index: 8429157 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7723. Min Range: -8.7723
Max Act: 8.2098. Min Act: -0.1700
Data Index: 265135 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7723. Min Range: -8.7723
Max Act: 8.2098. Min Act: -0.1700
Data Index: 472660 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7723. Min Range: -8.7723
Max Act: 8.2098. Min Act: -0.1700
Data Index: 6075410 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7723. Min Range: -8.7723
Max Act: 8.2098. Min Act: -0.1700
Data Index: 2309157 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7723. Min Range: -8.7723
Max Act: 8.2098. Min Act: -0.1700
Data Index: 555229 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7723. Min Range: -8.7723
Max Act: 8.2098. Min Act: -0.1700
Data Index: 1497369 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #19