Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4229 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7990. Min Range: -5.7990
Max Act: 5.7990. Min Act: -0.1700
Data Index: 3776072 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7990. Min Range: -5.7990
Max Act: 5.6427. Min Act: -0.1700
Data Index: 7674433 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7990. Min Range: -5.7990
Max Act: 5.6115. Min Act: -0.1700
Data Index: 3622322 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7990. Min Range: -5.7990
Max Act: 5.6115. Min Act: -0.1700
Data Index: 4362475 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7990. Min Range: -5.7990
Max Act: 5.5177. Min Act: -0.1700
Data Index: 7651422 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7990. Min Range: -5.7990
Max Act: 5.4552. Min Act: -0.1700
Data Index: 4922968 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7990. Min Range: -5.7990
Max Act: 5.4865. Min Act: -0.1700
Data Index: 1381510 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7990. Min Range: -5.7990
Max Act: 5.3927. Min Act: -0.1700
Data Index: 4570311 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7990. Min Range: -5.7990
Max Act: 5.4552. Min Act: -0.1700
Data Index: 941346 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7990. Min Range: -5.7990
Max Act: 5.3615. Min Act: -0.1700
Data Index: 3384161 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7990. Min Range: -5.7990
Max Act: 5.3615. Min Act: -0.1700
Data Index: 5533166 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7990. Min Range: -5.7990
Max Act: 5.3615. Min Act: -0.1700
Data Index: 4599740 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7990. Min Range: -5.7990
Max Act: 5.3302. Min Act: -0.1700
Data Index: 387962 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7990. Min Range: -5.7990
Max Act: 5.2990. Min Act: -0.1700
Data Index: 5562888 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7990. Min Range: -5.7990
Max Act: 5.2990. Min Act: -0.1700
Data Index: 4621793 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7990. Min Range: -5.7990
Max Act: 5.2990. Min Act: -0.1700
Data Index: 8017235 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7990. Min Range: -5.7990
Max Act: 5.2677. Min Act: -0.1700
Data Index: 8659049 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7990. Min Range: -5.7990
Max Act: 5.2677. Min Act: -0.1700
Data Index: 6806259 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7990. Min Range: -5.7990
Max Act: 5.2677. Min Act: -0.1700
Data Index: 5284935 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7990. Min Range: -5.7990
Max Act: 5.2365. Min Act: -0.1700
Data Index: 4638789 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #19