Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 506 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6019. Min Range: -6.6019
Max Act: 6.6019. Min Act: -0.1700
Data Index: 390393 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6019. Min Range: -6.6019
Max Act: 6.4769. Min Act: -0.1700
Data Index: 5498258 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6019. Min Range: -6.6019
Max Act: 6.3207. Min Act: -0.1700
Data Index: 34373 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6019. Min Range: -6.6019
Max Act: 6.3207. Min Act: -0.1700
Data Index: 2008817 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6019. Min Range: -6.6019
Max Act: 6.2582. Min Act: -0.1700
Data Index: 5004090 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6019. Min Range: -6.6019
Max Act: 6.2582. Min Act: -0.1700
Data Index: 3053655 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6019. Min Range: -6.6019
Max Act: 6.2582. Min Act: -0.1700
Data Index: 4751905 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6019. Min Range: -6.6019
Max Act: 6.1019. Min Act: -0.1700
Data Index: 5688385 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6019. Min Range: -6.6019
Max Act: 6.1332. Min Act: -0.1700
Data Index: 8338358 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6019. Min Range: -6.6019
Max Act: 6.1019. Min Act: -0.1700
Data Index: 211186 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6019. Min Range: -6.6019
Max Act: 6.1019. Min Act: -0.1700
Data Index: 2504576 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6019. Min Range: -6.6019
Max Act: 6.0394. Min Act: -0.1700
Data Index: 7595095 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6019. Min Range: -6.6019
Max Act: 6.0394. Min Act: -0.1700
Data Index: 4727445 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6019. Min Range: -6.6019
Max Act: 6.0394. Min Act: -0.1700
Data Index: 6463343 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6019. Min Range: -6.6019
Max Act: 6.0082. Min Act: -0.1700
Data Index: 958081 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6019. Min Range: -6.6019
Max Act: 6.0394. Min Act: -0.1700
Data Index: 6989274 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6019. Min Range: -6.6019
Max Act: 6.0394. Min Act: -0.1700
Data Index: 2427539 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6019. Min Range: -6.6019
Max Act: 6.0082. Min Act: -0.1700
Data Index: 7122648 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6019. Min Range: -6.6019
Max Act: 5.9457. Min Act: -0.1700
Data Index: 3504093 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6019. Min Range: -6.6019
Max Act: 5.9769. Min Act: -0.1700
Data Index: 3314905 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #19