Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2825 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7214. Min Range: -5.7214
Max Act: 5.7214. Min Act: -0.1700
Data Index: 1356569 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7214. Min Range: -5.7214
Max Act: 5.3776. Min Act: -0.1700
Data Index: 1280211 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7214. Min Range: -5.7214
Max Act: 5.4089. Min Act: -0.1700
Data Index: 2470804 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7214. Min Range: -5.7214
Max Act: 5.3776. Min Act: -0.1700
Data Index: 1252059 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7214. Min Range: -5.7214
Max Act: 5.1276. Min Act: -0.1700
Data Index: 4502417 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7214. Min Range: -5.7214
Max Act: 5.1276. Min Act: -0.1700
Data Index: 5110068 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7214. Min Range: -5.7214
Max Act: 5.1276. Min Act: -0.1700
Data Index: 3303839 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7214. Min Range: -5.7214
Max Act: 5.0651. Min Act: -0.1700
Data Index: 7604641 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7214. Min Range: -5.7214
Max Act: 5.0651. Min Act: -0.1700
Data Index: 3790349 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7214. Min Range: -5.7214
Max Act: 4.9714. Min Act: -0.1700
Data Index: 1286244 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7214. Min Range: -5.7214
Max Act: 5.0026. Min Act: -0.1700
Data Index: 738836 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7214. Min Range: -5.7214
Max Act: 4.9714. Min Act: -0.1700
Data Index: 7908056 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7214. Min Range: -5.7214
Max Act: 4.9401. Min Act: -0.1700
Data Index: 8704469 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7214. Min Range: -5.7214
Max Act: 4.9089. Min Act: -0.1700
Data Index: 8643068 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7214. Min Range: -5.7214
Max Act: 4.9401. Min Act: -0.1700
Data Index: 3372444 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7214. Min Range: -5.7214
Max Act: 4.9089. Min Act: -0.1700
Data Index: 710425 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7214. Min Range: -5.7214
Max Act: 4.8776. Min Act: -0.1700
Data Index: 4772330 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7214. Min Range: -5.7214
Max Act: 4.9089. Min Act: -0.1700
Data Index: 4921281 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7214. Min Range: -5.7214
Max Act: 4.8464. Min Act: -0.1700
Data Index: 4899331 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7214. Min Range: -5.7214
Max Act: 4.8464. Min Act: -0.1700
Data Index: 3202502 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #19