Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 176 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0525. Min Range: -4.0525
Max Act: 4.0525. Min Act: -0.1700
Data Index: 730559 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0525. Min Range: -4.0525
Max Act: 4.0525. Min Act: -0.1700
Data Index: 403567 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0525. Min Range: -4.0525
Max Act: 4.0212. Min Act: -0.1700
Data Index: 7324944 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0525. Min Range: -4.0525
Max Act: 4.0212. Min Act: -0.1700
Data Index: 8730279 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.9900. Min Act: -0.1700
Data Index: 3973720 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0525. Min Range: -4.0525
Max Act: 4.0212. Min Act: -0.1700
Data Index: 487626 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0525. Min Range: -4.0525
Max Act: 4.0212. Min Act: -0.1700
Data Index: 4396024 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.9900. Min Act: -0.1700
Data Index: 4760811 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.9900. Min Act: -0.1700
Data Index: 3768351 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.9900. Min Act: -0.1700
Data Index: 2444568 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.9900. Min Act: -0.1700
Data Index: 2355569 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.9900. Min Act: -0.1700
Data Index: 4339110 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.9900. Min Act: -0.1700
Data Index: 4401722 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.9587. Min Act: -0.1700
Data Index: 1071848 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.9587. Min Act: -0.1700
Data Index: 1031643 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.9587. Min Act: -0.1700
Data Index: 4682565 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.9587. Min Act: -0.1700
Data Index: 500979 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.9587. Min Act: -0.1700
Data Index: 2426216 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.9587. Min Act: -0.1700
Data Index: 2269498 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0525. Min Range: -4.0525
Max Act: 3.9587. Min Act: -0.1700
Data Index: 3819650 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19