Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5594. Min Range: -3.5594
Max Act: 3.5594. Min Act: -0.1700
Data Index: 4797376 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5594. Min Range: -3.5594
Max Act: 3.4968. Min Act: -0.1700
Data Index: 1349895 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5594. Min Range: -3.5594
Max Act: 3.4498. Min Act: -0.1700
Data Index: 7459703 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5594. Min Range: -3.5594
Max Act: 3.4341. Min Act: -0.1700
Data Index: 6449438 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5594. Min Range: -3.5594
Max Act: 3.3871. Min Act: -0.1700
Data Index: 6222502 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5594. Min Range: -3.5594
Max Act: 3.3243. Min Act: -0.1700
Data Index: 263004 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5594. Min Range: -3.5594
Max Act: 3.3086. Min Act: -0.1700
Data Index: 7425254 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5594. Min Range: -3.5594
Max Act: 3.3086. Min Act: -0.1700
Data Index: 3525833 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5594. Min Range: -3.5594
Max Act: 3.2772. Min Act: -0.1700
Data Index: 5294688 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5594. Min Range: -3.5594
Max Act: 3.2615. Min Act: -0.1700
Data Index: 8601150 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5594. Min Range: -3.5594
Max Act: 3.2615. Min Act: -0.1700
Data Index: 6685573 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5594. Min Range: -3.5594
Max Act: 3.2301. Min Act: -0.1700
Data Index: 2971582 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5594. Min Range: -3.5594
Max Act: 3.2458. Min Act: -0.1700
Data Index: 6956400 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5594. Min Range: -3.5594
Max Act: 3.2458. Min Act: -0.1700
Data Index: 5279848 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5594. Min Range: -3.5594
Max Act: 3.2301. Min Act: -0.1700
Data Index: 5127556 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5594. Min Range: -3.5594
Max Act: 3.2144. Min Act: -0.1700
Data Index: 8604121 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5594. Min Range: -3.5594
Max Act: 3.2144. Min Act: -0.1700
Data Index: 6551465 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5594. Min Range: -3.5594
Max Act: 3.1829. Min Act: -0.1700
Data Index: 3272920 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5594. Min Range: -3.5594
Max Act: 3.1672. Min Act: -0.1700
Data Index: 4370369 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5594. Min Range: -3.5594
Max Act: 3.1672. Min Act: -0.1700
Data Index: 3086656 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #19