Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4548 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.9929. Min Range: -7.9929
Max Act: 7.9929. Min Act: -0.1700
Data Index: 4152508 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9929. Min Range: -7.9929
Max Act: 7.8054. Min Act: -0.1700
Data Index: 2722450 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9929. Min Range: -7.9929
Max Act: 7.7429. Min Act: -0.1700
Data Index: 5736766 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9929. Min Range: -7.9929
Max Act: 7.7429. Min Act: -0.1700
Data Index: 8115807 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9929. Min Range: -7.9929
Max Act: 7.6804. Min Act: -0.1700
Data Index: 4796443 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9929. Min Range: -7.9929
Max Act: 7.6179. Min Act: -0.1700
Data Index: 5736764 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9929. Min Range: -7.9929
Max Act: 7.5554. Min Act: -0.1700
Data Index: 6471396 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9929. Min Range: -7.9929
Max Act: 7.4929. Min Act: -0.1700
Data Index: 1020210 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9929. Min Range: -7.9929
Max Act: 7.4929. Min Act: -0.1700
Data Index: 4152504 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9929. Min Range: -7.9929
Max Act: 7.4304. Min Act: -0.1700
Data Index: 4796449 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9929. Min Range: -7.9929
Max Act: 7.3679. Min Act: -0.1700
Data Index: 4261101 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9929. Min Range: -7.9929
Max Act: 7.3679. Min Act: -0.1700
Data Index: 8429278 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9929. Min Range: -7.9929
Max Act: 7.3679. Min Act: -0.1700
Data Index: 6471399 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9929. Min Range: -7.9929
Max Act: 7.3054. Min Act: -0.1700
Data Index: 6471392 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9929. Min Range: -7.9929
Max Act: 7.3054. Min Act: -0.1700
Data Index: 1160473 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9929. Min Range: -7.9929
Max Act: 7.2429. Min Act: -0.1700
Data Index: 6953810 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9929. Min Range: -7.9929
Max Act: 7.2429. Min Act: -0.1700
Data Index: 4796444 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9929. Min Range: -7.9929
Max Act: 7.1804. Min Act: -0.1700
Data Index: 1160477 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9929. Min Range: -7.9929
Max Act: 7.2429. Min Act: -0.1700
Data Index: 5736762 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9929. Min Range: -7.9929
Max Act: 7.2429. Min Act: -0.1700
Data Index: 2453327 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #19