Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3470 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2585. Min Range: -4.2585
Max Act: 4.2585. Min Act: -0.1700
Data Index: 1314270 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2585. Min Range: -4.2585
Max Act: 4.2273. Min Act: -0.1700
Data Index: 432348 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2585. Min Range: -4.2585
Max Act: 4.1648. Min Act: -0.1700
Data Index: 1939809 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2585. Min Range: -4.2585
Max Act: 4.1648. Min Act: -0.1700
Data Index: 2274219 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2585. Min Range: -4.2585
Max Act: 4.1335. Min Act: -0.1700
Data Index: 8399210 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2585. Min Range: -4.2585
Max Act: 4.1023. Min Act: -0.1700
Data Index: 5877202 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2585. Min Range: -4.2585
Max Act: 4.0710. Min Act: -0.1700
Data Index: 1892193 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2585. Min Range: -4.2585
Max Act: 4.0710. Min Act: -0.1700
Data Index: 625215 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2585. Min Range: -4.2585
Max Act: 4.0710. Min Act: -0.1700
Data Index: 4060456 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2585. Min Range: -4.2585
Max Act: 4.0397. Min Act: -0.1700
Data Index: 5543475 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2585. Min Range: -4.2585
Max Act: 4.0710. Min Act: -0.1700
Data Index: 1557982 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2585. Min Range: -4.2585
Max Act: 4.0710. Min Act: -0.1700
Data Index: 3082408 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2585. Min Range: -4.2585
Max Act: 4.0397. Min Act: -0.1700
Data Index: 1195674 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2585. Min Range: -4.2585
Max Act: 4.0397. Min Act: -0.1700
Data Index: 1120077 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2585. Min Range: -4.2585
Max Act: 4.0397. Min Act: -0.1700
Data Index: 245957 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2585. Min Range: -4.2585
Max Act: 4.0397. Min Act: -0.1700
Data Index: 8779451 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2585. Min Range: -4.2585
Max Act: 4.0397. Min Act: -0.1700
Data Index: 715351 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2585. Min Range: -4.2585
Max Act: 4.0397. Min Act: -0.1700
Data Index: 7952641 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2585. Min Range: -4.2585
Max Act: 4.0397. Min Act: -0.1700
Data Index: 4300096 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2585. Min Range: -4.2585
Max Act: 4.0397. Min Act: -0.1700
Data Index: 6891300 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19