Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2928 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6871. Min Range: -6.6871
Max Act: 6.6871. Min Act: -0.1700
Data Index: 4121836 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6871. Min Range: -6.6871
Max Act: 6.5621. Min Act: -0.1700
Data Index: 7183701 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6871. Min Range: -6.6871
Max Act: 6.4683. Min Act: -0.1700
Data Index: 7062520 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6871. Min Range: -6.6871
Max Act: 6.3433. Min Act: -0.1700
Data Index: 951897 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6871. Min Range: -6.6871
Max Act: 6.3433. Min Act: -0.1700
Data Index: 5348139 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6871. Min Range: -6.6871
Max Act: 6.2808. Min Act: -0.1700
Data Index: 2368784 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6871. Min Range: -6.6871
Max Act: 6.2183. Min Act: -0.1700
Data Index: 8774363 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6871. Min Range: -6.6871
Max Act: 6.0933. Min Act: -0.1700
Data Index: 1857188 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6871. Min Range: -6.6871
Max Act: 6.0621. Min Act: -0.1700
Data Index: 8426375 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6871. Min Range: -6.6871
Max Act: 6.0621. Min Act: -0.1700
Data Index: 4175308 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6871. Min Range: -6.6871
Max Act: 6.0308. Min Act: -0.1700
Data Index: 3585927 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6871. Min Range: -6.6871
Max Act: 5.9996. Min Act: -0.1700
Data Index: 3469733 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6871. Min Range: -6.6871
Max Act: 5.9683. Min Act: -0.1700
Data Index: 1308707 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6871. Min Range: -6.6871
Max Act: 5.9371. Min Act: -0.1700
Data Index: 6545818 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6871. Min Range: -6.6871
Max Act: 5.9058. Min Act: -0.1700
Data Index: 3830314 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6871. Min Range: -6.6871
Max Act: 5.9058. Min Act: -0.1700
Data Index: 1256243 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6871. Min Range: -6.6871
Max Act: 5.8746. Min Act: -0.1700
Data Index: 994797 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6871. Min Range: -6.6871
Max Act: 5.8746. Min Act: -0.1700
Data Index: 6805540 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6871. Min Range: -6.6871
Max Act: 5.8433. Min Act: -0.1700
Data Index: 7908033 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6871. Min Range: -6.6871
Max Act: 5.8746. Min Act: -0.1700
Data Index: 4331135 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19