Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3972 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1943. Min Range: -9.1943
Max Act: 9.1943. Min Act: -0.1700
Data Index: 1718231 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1943. Min Range: -9.1943
Max Act: 9.0693. Min Act: -0.1700
Data Index: 7168592 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1943. Min Range: -9.1943
Max Act: 8.8818. Min Act: -0.1700
Data Index: 5617211 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1943. Min Range: -9.1943
Max Act: 8.6943. Min Act: -0.1700
Data Index: 4445981 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1943. Min Range: -9.1943
Max Act: 8.6943. Min Act: -0.1700
Data Index: 1914003 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1943. Min Range: -9.1943
Max Act: 8.5068. Min Act: -0.1700
Data Index: 6766263 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1943. Min Range: -9.1943
Max Act: 8.5068. Min Act: -0.1700
Data Index: 7921317 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1943. Min Range: -9.1943
Max Act: 8.4443. Min Act: -0.1700
Data Index: 5066386 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1943. Min Range: -9.1943
Max Act: 8.4443. Min Act: -0.1700
Data Index: 8574532 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1943. Min Range: -9.1943
Max Act: 8.4443. Min Act: -0.1700
Data Index: 4216141 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1943. Min Range: -9.1943
Max Act: 8.3193. Min Act: -0.1700
Data Index: 2543798 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1943. Min Range: -9.1943
Max Act: 8.3193. Min Act: -0.1700
Data Index: 6441833 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1943. Min Range: -9.1943
Max Act: 8.3193. Min Act: -0.1700
Data Index: 5868059 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1943. Min Range: -9.1943
Max Act: 8.2568. Min Act: -0.1700
Data Index: 3250376 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1943. Min Range: -9.1943
Max Act: 8.2568. Min Act: -0.1700
Data Index: 3647771 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1943. Min Range: -9.1943
Max Act: 8.2568. Min Act: -0.1700
Data Index: 5585875 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1943. Min Range: -9.1943
Max Act: 8.2568. Min Act: -0.1700
Data Index: 704399 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1943. Min Range: -9.1943
Max Act: 8.1943. Min Act: -0.1700
Data Index: 2028815 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1943. Min Range: -9.1943
Max Act: 8.1943. Min Act: -0.1700
Data Index: 1866926 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1943. Min Range: -9.1943
Max Act: 8.1943. Min Act: -0.1700
Data Index: 6894609 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19