Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3522 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5974. Min Range: -5.5974
Max Act: 5.5974. Min Act: -0.1700
Data Index: 6929129 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5974. Min Range: -5.5974
Max Act: 5.5974. Min Act: -0.1700
Data Index: 7243935 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5974. Min Range: -5.5974
Max Act: 5.5349. Min Act: -0.1700
Data Index: 6963974 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5974. Min Range: -5.5974
Max Act: 5.4724. Min Act: -0.1700
Data Index: 8572010 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5974. Min Range: -5.5974
Max Act: 5.4724. Min Act: -0.1700
Data Index: 3310703 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5974. Min Range: -5.5974
Max Act: 5.4411. Min Act: -0.1700
Data Index: 8644135 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5974. Min Range: -5.5974
Max Act: 5.4411. Min Act: -0.1700
Data Index: 7977651 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5974. Min Range: -5.5974
Max Act: 5.3786. Min Act: -0.1700
Data Index: 947666 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5974. Min Range: -5.5974
Max Act: 5.4099. Min Act: -0.1700
Data Index: 8736582 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5974. Min Range: -5.5974
Max Act: 5.4099. Min Act: -0.1700
Data Index: 5125630 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5974. Min Range: -5.5974
Max Act: 5.3786. Min Act: -0.1700
Data Index: 5891147 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5974. Min Range: -5.5974
Max Act: 5.3786. Min Act: -0.1700
Data Index: 845276 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5974. Min Range: -5.5974
Max Act: 5.3786. Min Act: -0.1700
Data Index: 3614839 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5974. Min Range: -5.5974
Max Act: 5.3786. Min Act: -0.1700
Data Index: 5307846 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5974. Min Range: -5.5974
Max Act: 5.3474. Min Act: -0.1700
Data Index: 3750540 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5974. Min Range: -5.5974
Max Act: 5.3161. Min Act: -0.1700
Data Index: 3347053 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5974. Min Range: -5.5974
Max Act: 5.3474. Min Act: -0.1700
Data Index: 4241949 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5974. Min Range: -5.5974
Max Act: 5.3474. Min Act: -0.1700
Data Index: 813045 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5974. Min Range: -5.5974
Max Act: 5.3474. Min Act: -0.1700
Data Index: 4363104 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5974. Min Range: -5.5974
Max Act: 5.3474. Min Act: -0.1700
Data Index: 2180304 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #19