Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1596 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9888. Min Range: -8.9888
Max Act: 8.9888. Min Act: -0.1700
Data Index: 8445065 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9888. Min Range: -8.9888
Max Act: 8.9263. Min Act: -0.1700
Data Index: 1285402 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9888. Min Range: -8.9888
Max Act: 8.7388. Min Act: -0.1700
Data Index: 6812731 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9888. Min Range: -8.9888
Max Act: 8.6763. Min Act: -0.1700
Data Index: 5267758 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9888. Min Range: -8.9888
Max Act: 8.6763. Min Act: -0.1700
Data Index: 1963347 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9888. Min Range: -8.9888
Max Act: 8.6138. Min Act: -0.1700
Data Index: 1032592 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9888. Min Range: -8.9888
Max Act: 8.5513. Min Act: -0.1700
Data Index: 6982932 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9888. Min Range: -8.9888
Max Act: 8.4888. Min Act: -0.1700
Data Index: 2163706 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9888. Min Range: -8.9888
Max Act: 8.4888. Min Act: -0.1700
Data Index: 1885160 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9888. Min Range: -8.9888
Max Act: 8.4263. Min Act: -0.1700
Data Index: 4282620 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9888. Min Range: -8.9888
Max Act: 8.4263. Min Act: -0.1700
Data Index: 2746817 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9888. Min Range: -8.9888
Max Act: 8.4888. Min Act: -0.1700
Data Index: 5086376 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9888. Min Range: -8.9888
Max Act: 8.3638. Min Act: -0.1700
Data Index: 1656039 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9888. Min Range: -8.9888
Max Act: 8.3013. Min Act: -0.1700
Data Index: 4645289 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9888. Min Range: -8.9888
Max Act: 8.3013. Min Act: -0.1700
Data Index: 958688 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9888. Min Range: -8.9888
Max Act: 8.3013. Min Act: -0.1700
Data Index: 1245265 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9888. Min Range: -8.9888
Max Act: 8.3013. Min Act: -0.1700
Data Index: 6967778 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9888. Min Range: -8.9888
Max Act: 8.2388. Min Act: -0.1700
Data Index: 8786379 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9888. Min Range: -8.9888
Max Act: 8.2388. Min Act: -0.1700
Data Index: 26413 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9888. Min Range: -8.9888
Max Act: 8.1763. Min Act: -0.1700
Data Index: 180365 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #19