Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 395 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.0656. Min Range: -2.0656
Max Act: 2.0656. Min Act: -0.1700
Data Index: 7245 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0656. Min Range: -2.0656
Max Act: 2.0319. Min Act: -0.1700
Data Index: 5730533 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0656. Min Range: -2.0656
Max Act: 1.9982. Min Act: -0.1700
Data Index: 8116617 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0656. Min Range: -2.0656
Max Act: 1.9813. Min Act: -0.1699
Data Index: 1008221 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0656. Min Range: -2.0656
Max Act: 1.9643. Min Act: -0.1700
Data Index: 6567806 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0656. Min Range: -2.0656
Max Act: 1.9304. Min Act: -0.1700
Data Index: 1655439 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0656. Min Range: -2.0656
Max Act: 1.9474. Min Act: -0.1699
Data Index: 8662873 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0656. Min Range: -2.0656
Max Act: 1.9134. Min Act: -0.1686
Data Index: 5194682 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0656. Min Range: -2.0656
Max Act: 1.9134. Min Act: -0.1700
Data Index: 4619740 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0656. Min Range: -2.0656
Max Act: 1.8963. Min Act: -0.1700
Data Index: 5196067 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0656. Min Range: -2.0656
Max Act: 1.8963. Min Act: -0.1700
Data Index: 3332268 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0656. Min Range: -2.0656
Max Act: 1.8963. Min Act: -0.1700
Data Index: 2184410 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0656. Min Range: -2.0656
Max Act: 1.8963. Min Act: -0.1700
Data Index: 1864471 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0656. Min Range: -2.0656
Max Act: 1.8963. Min Act: -0.1700
Data Index: 3361938 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0656. Min Range: -2.0656
Max Act: 1.8792. Min Act: -0.1700
Data Index: 5971383 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0656. Min Range: -2.0656
Max Act: 1.8792. Min Act: -0.1700
Data Index: 4913135 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0656. Min Range: -2.0656
Max Act: 1.8792. Min Act: -0.1699
Data Index: 6432718 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0656. Min Range: -2.0656
Max Act: 1.8792. Min Act: -0.1700
Data Index: 7490943 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0656. Min Range: -2.0656
Max Act: 1.8792. Min Act: -0.1700
Data Index: 3685225 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0656. Min Range: -2.0656
Max Act: 1.8621. Min Act: -0.1700
Data Index: 1366822 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19