Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4339 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2654. Min Range: -7.2654
Max Act: 7.2654. Min Act: -0.1700
Data Index: 1903933 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2654. Min Range: -7.2654
Max Act: 6.7654. Min Act: -0.1700
Data Index: 533225 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2654. Min Range: -7.2654
Max Act: 6.6092. Min Act: -0.1700
Data Index: 452774 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2654. Min Range: -7.2654
Max Act: 6.6092. Min Act: -0.1700
Data Index: 4970341 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2654. Min Range: -7.2654
Max Act: 6.5154. Min Act: -0.1700
Data Index: 5092075 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2654. Min Range: -7.2654
Max Act: 6.5467. Min Act: -0.1700
Data Index: 3581356 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2654. Min Range: -7.2654
Max Act: 6.5467. Min Act: -0.1700
Data Index: 7623653 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2654. Min Range: -7.2654
Max Act: 6.5154. Min Act: -0.1700
Data Index: 7162360 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2654. Min Range: -7.2654
Max Act: 6.4842. Min Act: -0.1700
Data Index: 162672 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2654. Min Range: -7.2654
Max Act: 6.4842. Min Act: -0.1700
Data Index: 1297513 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2654. Min Range: -7.2654
Max Act: 6.4529. Min Act: -0.1700
Data Index: 2505953 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2654. Min Range: -7.2654
Max Act: 6.4529. Min Act: -0.1700
Data Index: 691374 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2654. Min Range: -7.2654
Max Act: 6.4529. Min Act: -0.1700
Data Index: 5514391 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2654. Min Range: -7.2654
Max Act: 6.3904. Min Act: -0.1700
Data Index: 5565734 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2654. Min Range: -7.2654
Max Act: 6.3592. Min Act: -0.1700
Data Index: 8374605 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2654. Min Range: -7.2654
Max Act: 6.4217. Min Act: -0.1700
Data Index: 4624168 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2654. Min Range: -7.2654
Max Act: 6.3592. Min Act: -0.1700
Data Index: 3781617 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2654. Min Range: -7.2654
Max Act: 6.3279. Min Act: -0.1700
Data Index: 1887081 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2654. Min Range: -7.2654
Max Act: 6.2654. Min Act: -0.1700
Data Index: 4839251 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2654. Min Range: -7.2654
Max Act: 6.2967. Min Act: -0.1700
Data Index: 3716227 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #19