Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5075 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4488. Min Range: -3.4488
Max Act: 3.4331. Min Act: -0.1700
Data Index: 1597509 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4488. Min Range: -3.4488
Max Act: 3.4488. Min Act: -0.1700
Data Index: 4942620 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4488. Min Range: -3.4488
Max Act: 3.4018. Min Act: -0.1700
Data Index: 8427462 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4488. Min Range: -3.4488
Max Act: 3.4018. Min Act: -0.1700
Data Index: 4412349 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4488. Min Range: -3.4488
Max Act: 3.3704. Min Act: -0.1700
Data Index: 8591702 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4488. Min Range: -3.4488
Max Act: 3.3704. Min Act: -0.1700
Data Index: 3338035 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4488. Min Range: -3.4488
Max Act: 3.3234. Min Act: -0.1700
Data Index: 1832724 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4488. Min Range: -3.4488
Max Act: 3.3077. Min Act: -0.1700
Data Index: 3899650 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4488. Min Range: -3.4488
Max Act: 3.2920. Min Act: -0.1700
Data Index: 3181063 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4488. Min Range: -3.4488
Max Act: 3.2920. Min Act: -0.1700
Data Index: 3839060 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4488. Min Range: -3.4488
Max Act: 3.2920. Min Act: -0.1700
Data Index: 4066315 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4488. Min Range: -3.4488
Max Act: 3.2920. Min Act: -0.1700
Data Index: 911676 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4488. Min Range: -3.4488
Max Act: 3.2763. Min Act: -0.1700
Data Index: 8812239 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4488. Min Range: -3.4488
Max Act: 3.2763. Min Act: -0.1700
Data Index: 7311390 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4488. Min Range: -3.4488
Max Act: 3.2605. Min Act: -0.1700
Data Index: 2888363 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4488. Min Range: -3.4488
Max Act: 3.2605. Min Act: -0.1700
Data Index: 8012942 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4488. Min Range: -3.4488
Max Act: 3.2605. Min Act: -0.1700
Data Index: 4273999 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4488. Min Range: -3.4488
Max Act: 3.2605. Min Act: -0.1700
Data Index: 5664033 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4488. Min Range: -3.4488
Max Act: 3.2605. Min Act: -0.1700
Data Index: 1098184 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4488. Min Range: -3.4488
Max Act: 3.2605. Min Act: -0.1700
Data Index: 6411282 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #19