Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3326 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8683. Min Range: -4.8683
Max Act: 4.8371. Min Act: -0.1700
Data Index: 4477701 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8683. Min Range: -4.8683
Max Act: 4.8683. Min Act: -0.1700
Data Index: 7339398 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8683. Min Range: -4.8683
Max Act: 4.8371. Min Act: -0.1700
Data Index: 4477722 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8683. Min Range: -4.8683
Max Act: 4.7433. Min Act: -0.1700
Data Index: 7184558 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8683. Min Range: -4.8683
Max Act: 4.6496. Min Act: -0.1700
Data Index: 3993894 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8683. Min Range: -4.8683
Max Act: 4.6183. Min Act: -0.1700
Data Index: 1338821 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8683. Min Range: -4.8683
Max Act: 4.5871. Min Act: -0.1700
Data Index: 5928996 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8683. Min Range: -4.8683
Max Act: 4.4933. Min Act: -0.1700
Data Index: 5978331 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8683. Min Range: -4.8683
Max Act: 4.4933. Min Act: -0.1700
Data Index: 7245580 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8683. Min Range: -4.8683
Max Act: 4.4933. Min Act: -0.1700
Data Index: 6994035 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8683. Min Range: -4.8683
Max Act: 4.4621. Min Act: -0.1700
Data Index: 8209124 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8683. Min Range: -4.8683
Max Act: 4.4933. Min Act: -0.1700
Data Index: 4145448 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8683. Min Range: -4.8683
Max Act: 4.4621. Min Act: -0.1700
Data Index: 6975405 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8683. Min Range: -4.8683
Max Act: 4.4933. Min Act: -0.1700
Data Index: 3237351 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8683. Min Range: -4.8683
Max Act: 4.4621. Min Act: -0.1700
Data Index: 6087485 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8683. Min Range: -4.8683
Max Act: 4.4308. Min Act: -0.1700
Data Index: 3305216 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8683. Min Range: -4.8683
Max Act: 4.4308. Min Act: -0.1700
Data Index: 6233462 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8683. Min Range: -4.8683
Max Act: 4.4308. Min Act: -0.1700
Data Index: 204788 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8683. Min Range: -4.8683
Max Act: 4.3996. Min Act: -0.1700
Data Index: 4001795 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8683. Min Range: -4.8683
Max Act: 4.3996. Min Act: -0.1700
Data Index: 6786374 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #19