Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2008 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4400. Min Range: -7.4400
Max Act: 7.4400. Min Act: -0.1700
Data Index: 4670193 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4400. Min Range: -7.4400
Max Act: 7.4087. Min Act: -0.1700
Data Index: 4255803 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4400. Min Range: -7.4400
Max Act: 7.3775. Min Act: -0.1700
Data Index: 3422146 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4400. Min Range: -7.4400
Max Act: 7.0962. Min Act: -0.1700
Data Index: 2071731 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4400. Min Range: -7.4400
Max Act: 7.0337. Min Act: -0.1700
Data Index: 5932206 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4400. Min Range: -7.4400
Max Act: 7.0337. Min Act: -0.1700
Data Index: 2719657 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4400. Min Range: -7.4400
Max Act: 7.0025. Min Act: -0.1700
Data Index: 2650315 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4400. Min Range: -7.4400
Max Act: 7.0025. Min Act: -0.1700
Data Index: 4867748 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4400. Min Range: -7.4400
Max Act: 6.8462. Min Act: -0.1700
Data Index: 6953161 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4400. Min Range: -7.4400
Max Act: 6.8775. Min Act: -0.1700
Data Index: 3739781 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4400. Min Range: -7.4400
Max Act: 6.8775. Min Act: -0.1700
Data Index: 167357 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4400. Min Range: -7.4400
Max Act: 6.8775. Min Act: -0.1700
Data Index: 5739787 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4400. Min Range: -7.4400
Max Act: 6.8775. Min Act: -0.1700
Data Index: 7518669 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4400. Min Range: -7.4400
Max Act: 6.8150. Min Act: -0.1700
Data Index: 1176182 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4400. Min Range: -7.4400
Max Act: 6.7837. Min Act: -0.1700
Data Index: 7196167 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4400. Min Range: -7.4400
Max Act: 6.7837. Min Act: -0.1700
Data Index: 875887 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4400. Min Range: -7.4400
Max Act: 6.7525. Min Act: -0.1700
Data Index: 4916348 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4400. Min Range: -7.4400
Max Act: 6.7212. Min Act: -0.1700
Data Index: 199226 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4400. Min Range: -7.4400
Max Act: 6.7212. Min Act: -0.1700
Data Index: 7500694 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4400. Min Range: -7.4400
Max Act: 6.7212. Min Act: -0.1700
Data Index: 2490212 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #19