Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2906 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7450. Min Range: -6.7450
Max Act: 6.7450. Min Act: -0.1700
Data Index: 3027966 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7450. Min Range: -6.7450
Max Act: 6.5888. Min Act: -0.1700
Data Index: 7101984 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7450. Min Range: -6.7450
Max Act: 6.4013. Min Act: -0.1700
Data Index: 819390 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7450. Min Range: -6.7450
Max Act: 6.2763. Min Act: -0.1700
Data Index: 7866744 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7450. Min Range: -6.7450
Max Act: 6.2763. Min Act: -0.1700
Data Index: 1147293 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7450. Min Range: -6.7450
Max Act: 6.1513. Min Act: -0.1700
Data Index: 7380089 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7450. Min Range: -6.7450
Max Act: 6.1200. Min Act: -0.1700
Data Index: 7902351 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7450. Min Range: -6.7450
Max Act: 6.0575. Min Act: -0.1700
Data Index: 7703115 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7450. Min Range: -6.7450
Max Act: 6.0575. Min Act: -0.1700
Data Index: 8379177 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7450. Min Range: -6.7450
Max Act: 6.0263. Min Act: -0.1700
Data Index: 434881 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7450. Min Range: -6.7450
Max Act: 6.0263. Min Act: -0.1700
Data Index: 664195 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7450. Min Range: -6.7450
Max Act: 6.0263. Min Act: -0.1700
Data Index: 214235 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7450. Min Range: -6.7450
Max Act: 5.9950. Min Act: -0.1700
Data Index: 6499385 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7450. Min Range: -6.7450
Max Act: 5.9950. Min Act: -0.1700
Data Index: 5191647 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7450. Min Range: -6.7450
Max Act: 5.9638. Min Act: -0.1700
Data Index: 2228358 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7450. Min Range: -6.7450
Max Act: 5.9638. Min Act: -0.1700
Data Index: 59959 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7450. Min Range: -6.7450
Max Act: 5.9325. Min Act: -0.1700
Data Index: 1234105 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7450. Min Range: -6.7450
Max Act: 5.9325. Min Act: -0.1700
Data Index: 6431955 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7450. Min Range: -6.7450
Max Act: 5.8700. Min Act: -0.1700
Data Index: 5949660 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7450. Min Range: -6.7450
Max Act: 5.8700. Min Act: -0.1700
Data Index: 6737904 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #19