Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1726 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0567. Min Range: -5.0567
Max Act: 5.0567. Min Act: -0.1700
Data Index: 1521914 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0567. Min Range: -5.0567
Max Act: 5.0567. Min Act: -0.1700
Data Index: 3568961 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0567. Min Range: -5.0567
Max Act: 4.8380. Min Act: -0.1700
Data Index: 2778828 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0567. Min Range: -5.0567
Max Act: 4.8067. Min Act: -0.1700
Data Index: 3017038 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0567. Min Range: -5.0567
Max Act: 4.8067. Min Act: -0.1700
Data Index: 7689019 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0567. Min Range: -5.0567
Max Act: 4.7442. Min Act: -0.1700
Data Index: 6191338 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0567. Min Range: -5.0567
Max Act: 4.6817. Min Act: -0.1700
Data Index: 1389183 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0567. Min Range: -5.0567
Max Act: 4.6817. Min Act: -0.1700
Data Index: 5825982 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0567. Min Range: -5.0567
Max Act: 4.6817. Min Act: -0.1700
Data Index: 2234250 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0567. Min Range: -5.0567
Max Act: 4.6505. Min Act: -0.1700
Data Index: 2925608 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0567. Min Range: -5.0567
Max Act: 4.6505. Min Act: -0.1700
Data Index: 3235259 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0567. Min Range: -5.0567
Max Act: 4.6505. Min Act: -0.1700
Data Index: 1314197 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0567. Min Range: -5.0567
Max Act: 4.6505. Min Act: -0.1700
Data Index: 4755915 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0567. Min Range: -5.0567
Max Act: 4.6505. Min Act: -0.1700
Data Index: 6940617 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0567. Min Range: -5.0567
Max Act: 4.6192. Min Act: -0.1700
Data Index: 5566819 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0567. Min Range: -5.0567
Max Act: 4.6192. Min Act: -0.1700
Data Index: 2841972 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0567. Min Range: -5.0567
Max Act: 4.5879. Min Act: -0.1700
Data Index: 1360167 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0567. Min Range: -5.0567
Max Act: 4.5567. Min Act: -0.1700
Data Index: 3586886 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0567. Min Range: -5.0567
Max Act: 4.5567. Min Act: -0.1700
Data Index: 3689101 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0567. Min Range: -5.0567
Max Act: 4.5879. Min Act: -0.1700
Data Index: 6867280 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #19