Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5704 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6545. Min Range: -6.6545
Max Act: 6.6545. Min Act: -0.1700
Data Index: 2686886 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6545. Min Range: -6.6545
Max Act: 6.5608. Min Act: -0.1700
Data Index: 4803213 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6545. Min Range: -6.6545
Max Act: 6.4983. Min Act: -0.1700
Data Index: 4021438 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6545. Min Range: -6.6545
Max Act: 6.4358. Min Act: -0.1700
Data Index: 5456016 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6545. Min Range: -6.6545
Max Act: 6.4045. Min Act: -0.1700
Data Index: 240222 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6545. Min Range: -6.6545
Max Act: 6.3733. Min Act: -0.1700
Data Index: 6266751 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6545. Min Range: -6.6545
Max Act: 6.3733. Min Act: -0.1700
Data Index: 5015614 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6545. Min Range: -6.6545
Max Act: 6.2795. Min Act: -0.1700
Data Index: 5115315 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6545. Min Range: -6.6545
Max Act: 6.2795. Min Act: -0.1700
Data Index: 2204697 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6545. Min Range: -6.6545
Max Act: 6.2483. Min Act: -0.1700
Data Index: 6007998 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6545. Min Range: -6.6545
Max Act: 6.2483. Min Act: -0.1700
Data Index: 2447597 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6545. Min Range: -6.6545
Max Act: 6.2170. Min Act: -0.1700
Data Index: 5007174 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6545. Min Range: -6.6545
Max Act: 6.2170. Min Act: -0.1700
Data Index: 6767283 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6545. Min Range: -6.6545
Max Act: 6.1858. Min Act: -0.1700
Data Index: 8568728 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6545. Min Range: -6.6545
Max Act: 6.1858. Min Act: -0.1700
Data Index: 5147472 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6545. Min Range: -6.6545
Max Act: 6.1858. Min Act: -0.1700
Data Index: 6741375 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6545. Min Range: -6.6545
Max Act: 6.2170. Min Act: -0.1700
Data Index: 3206581 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6545. Min Range: -6.6545
Max Act: 6.1545. Min Act: -0.1700
Data Index: 7086442 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6545. Min Range: -6.6545
Max Act: 6.1233. Min Act: -0.1700
Data Index: 5535779 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6545. Min Range: -6.6545
Max Act: 6.0920. Min Act: -0.1700
Data Index: 1323215 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #19