Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1996 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2276. Min Range: -8.2276
Max Act: 8.2276. Min Act: -0.1700
Data Index: 992598 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2276. Min Range: -8.2276
Max Act: 8.0089. Min Act: -0.1700
Data Index: 6333161 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2276. Min Range: -8.2276
Max Act: 7.6964. Min Act: -0.1700
Data Index: 3431241 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2276. Min Range: -8.2276
Max Act: 7.6651. Min Act: -0.1700
Data Index: 3350820 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2276. Min Range: -8.2276
Max Act: 7.4776. Min Act: -0.1700
Data Index: 302251 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2276. Min Range: -8.2276
Max Act: 7.4464. Min Act: -0.1700
Data Index: 4209265 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2276. Min Range: -8.2276
Max Act: 7.4464. Min Act: -0.1700
Data Index: 6424746 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2276. Min Range: -8.2276
Max Act: 7.3526. Min Act: -0.1700
Data Index: 6058710 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2276. Min Range: -8.2276
Max Act: 7.3526. Min Act: -0.1700
Data Index: 621602 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2276. Min Range: -8.2276
Max Act: 7.3526. Min Act: -0.1700
Data Index: 2600529 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2276. Min Range: -8.2276
Max Act: 7.3526. Min Act: -0.1700
Data Index: 7606318 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2276. Min Range: -8.2276
Max Act: 7.3526. Min Act: -0.1700
Data Index: 4925026 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2276. Min Range: -8.2276
Max Act: 7.3526. Min Act: -0.1700
Data Index: 350761 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2276. Min Range: -8.2276
Max Act: 7.2901. Min Act: -0.1700
Data Index: 7171398 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2276. Min Range: -8.2276
Max Act: 7.3214. Min Act: -0.1700
Data Index: 2785051 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2276. Min Range: -8.2276
Max Act: 7.2589. Min Act: -0.1700
Data Index: 8545969 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2276. Min Range: -8.2276
Max Act: 7.2589. Min Act: -0.1700
Data Index: 7908598 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2276. Min Range: -8.2276
Max Act: 7.2589. Min Act: -0.1700
Data Index: 3722676 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2276. Min Range: -8.2276
Max Act: 7.2589. Min Act: -0.1700
Data Index: 3088994 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2276. Min Range: -8.2276
Max Act: 7.2276. Min Act: -0.1700
Data Index: 5831526 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #19