Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2334 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 8.1994. Min Range: -8.1994
Max Act: 8.1994. Min Act: -0.1700
Data Index: 782767 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1994. Min Range: -8.1994
Max Act: 8.1056. Min Act: -0.1700
Data Index: 1667690 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1994. Min Range: -8.1994
Max Act: 8.1681. Min Act: -0.1700
Data Index: 782768 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1994. Min Range: -8.1994
Max Act: 8.0119. Min Act: -0.1700
Data Index: 7605473 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1994. Min Range: -8.1994
Max Act: 7.9806. Min Act: -0.1700
Data Index: 8077822 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1994. Min Range: -8.1994
Max Act: 7.9494. Min Act: -0.1700
Data Index: 1246649 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1994. Min Range: -8.1994
Max Act: 7.9494. Min Act: -0.1700
Data Index: 1667689 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1994. Min Range: -8.1994
Max Act: 7.9806. Min Act: -0.1700
Data Index: 582696 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1994. Min Range: -8.1994
Max Act: 7.8869. Min Act: -0.1700
Data Index: 7411488 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1994. Min Range: -8.1994
Max Act: 7.8869. Min Act: -0.1700
Data Index: 7738100 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1994. Min Range: -8.1994
Max Act: 7.7931. Min Act: -0.1700
Data Index: 8061595 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1994. Min Range: -8.1994
Max Act: 7.8244. Min Act: -0.1700
Data Index: 1773519 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1994. Min Range: -8.1994
Max Act: 7.8556. Min Act: -0.1700
Data Index: 1622252 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1994. Min Range: -8.1994
Max Act: 7.8244. Min Act: -0.1700
Data Index: 7976022 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1994. Min Range: -8.1994
Max Act: 7.8244. Min Act: -0.1700
Data Index: 3672159 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1994. Min Range: -8.1994
Max Act: 7.7931. Min Act: -0.1700
Data Index: 7664259 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1994. Min Range: -8.1994
Max Act: 7.8244. Min Act: -0.1700
Data Index: 5790527 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1994. Min Range: -8.1994
Max Act: 7.7619. Min Act: -0.1700
Data Index: 1436576 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1994. Min Range: -8.1994
Max Act: 7.7931. Min Act: -0.1700
Data Index: 5629250 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1994. Min Range: -8.1994
Max Act: 7.8244. Min Act: -0.1700
Data Index: 1780776 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #19