Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3504 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4613. Min Range: -6.4613
Max Act: 6.4613. Min Act: -0.1700
Data Index: 7891241 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4613. Min Range: -6.4613
Max Act: 6.3051. Min Act: -0.1700
Data Index: 7526080 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4613. Min Range: -6.4613
Max Act: 6.2738. Min Act: -0.1700
Data Index: 7754755 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4613. Min Range: -6.4613
Max Act: 6.2738. Min Act: -0.1700
Data Index: 1935137 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4613. Min Range: -6.4613
Max Act: 6.2738. Min Act: -0.1700
Data Index: 6001662 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4613. Min Range: -6.4613
Max Act: 6.1488. Min Act: -0.1700
Data Index: 7857898 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4613. Min Range: -6.4613
Max Act: 6.1176. Min Act: -0.1700
Data Index: 1633981 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4613. Min Range: -6.4613
Max Act: 6.0863. Min Act: -0.1700
Data Index: 8788537 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4613. Min Range: -6.4613
Max Act: 6.0863. Min Act: -0.1700
Data Index: 1531924 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4613. Min Range: -6.4613
Max Act: 5.9926. Min Act: -0.1700
Data Index: 5132598 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4613. Min Range: -6.4613
Max Act: 6.0238. Min Act: -0.1700
Data Index: 1374253 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4613. Min Range: -6.4613
Max Act: 5.9301. Min Act: -0.1700
Data Index: 2627097 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4613. Min Range: -6.4613
Max Act: 5.8988. Min Act: -0.1700
Data Index: 8308611 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4613. Min Range: -6.4613
Max Act: 5.8988. Min Act: -0.1700
Data Index: 2738394 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4613. Min Range: -6.4613
Max Act: 5.8051. Min Act: -0.1700
Data Index: 7891243 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4613. Min Range: -6.4613
Max Act: 5.8988. Min Act: -0.1700
Data Index: 5821773 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4613. Min Range: -6.4613
Max Act: 5.8051. Min Act: -0.1700
Data Index: 5931327 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4613. Min Range: -6.4613
Max Act: 5.8051. Min Act: -0.1700
Data Index: 6308760 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4613. Min Range: -6.4613
Max Act: 5.8051. Min Act: -0.1700
Data Index: 3124097 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4613. Min Range: -6.4613
Max Act: 5.8051. Min Act: -0.1700
Data Index: 8029657 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #19