Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3956 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.2457. Min Range: -2.2457
Max Act: 2.2457. Min Act: -0.1700
Data Index: 4984757 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.2457. Min Range: -2.2457
Max Act: 2.1960. Min Act: -0.1700
Data Index: 7827964 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.2457. Min Range: -2.2457
Max Act: 2.1960. Min Act: -0.1700
Data Index: 2168870 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.2457. Min Range: -2.2457
Max Act: 2.1628. Min Act: -0.1700
Data Index: 2901993 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.2457. Min Range: -2.2457
Max Act: 2.1294. Min Act: -0.1700
Data Index: 1620978 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.2457. Min Range: -2.2457
Max Act: 2.1127. Min Act: -0.1700
Data Index: 3619407 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.2457. Min Range: -2.2457
Max Act: 2.0960. Min Act: -0.1700
Data Index: 3015196 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.2457. Min Range: -2.2457
Max Act: 2.0288. Min Act: -0.1699
Data Index: 2931346 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.2457. Min Range: -2.2457
Max Act: 2.0288. Min Act: -0.1700
Data Index: 5762390 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.2457. Min Range: -2.2457
Max Act: 2.0288. Min Act: -0.1700
Data Index: 8710415 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.2457. Min Range: -2.2457
Max Act: 2.0288. Min Act: -0.1696
Data Index: 5403019 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.2457. Min Range: -2.2457
Max Act: 1.9781. Min Act: -0.1699
Data Index: 749462 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.2457. Min Range: -2.2457
Max Act: 1.9781. Min Act: -0.1700
Data Index: 5540028 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.2457. Min Range: -2.2457
Max Act: 1.9781. Min Act: -0.1700
Data Index: 4399588 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.2457. Min Range: -2.2457
Max Act: 1.9612. Min Act: -0.1700
Data Index: 4605981 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.2457. Min Range: -2.2457
Max Act: 1.9612. Min Act: -0.1696
Data Index: 7824225 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.2457. Min Range: -2.2457
Max Act: 1.9272. Min Act: -0.1695
Data Index: 871992 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.2457. Min Range: -2.2457
Max Act: 1.9442. Min Act: -0.1700
Data Index: 6445703 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.2457. Min Range: -2.2457
Max Act: 1.9272. Min Act: -0.1699
Data Index: 8545102 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.2457. Min Range: -2.2457
Max Act: 1.9272. Min Act: -0.1700
Data Index: 7691168 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #19