Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4082 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8728. Min Range: -8.8728
Max Act: 8.8728. Min Act: -0.1700
Data Index: 8019568 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8728. Min Range: -8.8728
Max Act: 8.8728. Min Act: -0.1700
Data Index: 7064004 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8728. Min Range: -8.8728
Max Act: 8.7478. Min Act: -0.1700
Data Index: 7867062 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8728. Min Range: -8.8728
Max Act: 8.4978. Min Act: -0.1700
Data Index: 870896 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8728. Min Range: -8.8728
Max Act: 8.4353. Min Act: -0.1700
Data Index: 8344137 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8728. Min Range: -8.8728
Max Act: 8.4353. Min Act: -0.1700
Data Index: 8516819 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8728. Min Range: -8.8728
Max Act: 8.3728. Min Act: -0.1700
Data Index: 6510734 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8728. Min Range: -8.8728
Max Act: 8.3728. Min Act: -0.1700
Data Index: 258789 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8728. Min Range: -8.8728
Max Act: 8.3728. Min Act: -0.1700
Data Index: 1975823 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8728. Min Range: -8.8728
Max Act: 8.3103. Min Act: -0.1700
Data Index: 810984 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8728. Min Range: -8.8728
Max Act: 8.3103. Min Act: -0.1700
Data Index: 8066927 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8728. Min Range: -8.8728
Max Act: 8.3103. Min Act: -0.1700
Data Index: 5593957 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8728. Min Range: -8.8728
Max Act: 8.3103. Min Act: -0.1700
Data Index: 4524701 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8728. Min Range: -8.8728
Max Act: 8.2478. Min Act: -0.1700
Data Index: 3459371 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8728. Min Range: -8.8728
Max Act: 8.2478. Min Act: -0.1700
Data Index: 5919309 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8728. Min Range: -8.8728
Max Act: 8.2166. Min Act: -0.1700
Data Index: 2994795 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8728. Min Range: -8.8728
Max Act: 8.2166. Min Act: -0.1700
Data Index: 1775613 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8728. Min Range: -8.8728
Max Act: 8.1541. Min Act: -0.1700
Data Index: 6152156 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8728. Min Range: -8.8728
Max Act: 8.2166. Min Act: -0.1700
Data Index: 1995871 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8728. Min Range: -8.8728
Max Act: 8.2166. Min Act: -0.1700
Data Index: 847836 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #19