Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3578 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4614. Min Range: -5.4614
Max Act: 5.4302. Min Act: -0.1700
Data Index: 2909243 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4614. Min Range: -5.4614
Max Act: 5.4614. Min Act: -0.1700
Data Index: 3896439 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4614. Min Range: -5.4614
Max Act: 5.3677. Min Act: -0.1700
Data Index: 5953178 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4614. Min Range: -5.4614
Max Act: 5.2739. Min Act: -0.1700
Data Index: 6763846 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4614. Min Range: -5.4614
Max Act: 5.2114. Min Act: -0.1700
Data Index: 6626340 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4614. Min Range: -5.4614
Max Act: 5.1802. Min Act: -0.1700
Data Index: 6936094 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4614. Min Range: -5.4614
Max Act: 5.1802. Min Act: -0.1700
Data Index: 7482837 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4614. Min Range: -5.4614
Max Act: 5.1489. Min Act: -0.1700
Data Index: 7348500 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4614. Min Range: -5.4614
Max Act: 5.1489. Min Act: -0.1700
Data Index: 8470200 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4614. Min Range: -5.4614
Max Act: 5.1177. Min Act: -0.1700
Data Index: 4381931 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4614. Min Range: -5.4614
Max Act: 5.1177. Min Act: -0.1700
Data Index: 1780389 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4614. Min Range: -5.4614
Max Act: 5.0864. Min Act: -0.1700
Data Index: 7348502 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4614. Min Range: -5.4614
Max Act: 5.1489. Min Act: -0.1700
Data Index: 3389198 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4614. Min Range: -5.4614
Max Act: 5.0552. Min Act: -0.1700
Data Index: 6173203 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4614. Min Range: -5.4614
Max Act: 5.0864. Min Act: -0.1700
Data Index: 265028 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4614. Min Range: -5.4614
Max Act: 5.0864. Min Act: -0.1699
Data Index: 8225949 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4614. Min Range: -5.4614
Max Act: 5.0552. Min Act: -0.1700
Data Index: 6061596 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4614. Min Range: -5.4614
Max Act: 5.0552. Min Act: -0.1700
Data Index: 8650051 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4614. Min Range: -5.4614
Max Act: 5.0552. Min Act: -0.1700
Data Index: 6152845 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4614. Min Range: -5.4614
Max Act: 5.0552. Min Act: -0.1700
Data Index: 892123 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #19