Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3441 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.4967. Min Range: -2.4967
Max Act: 2.4967. Min Act: -0.1700
Data Index: 220426 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.4967. Min Range: -2.4967
Max Act: 2.4805. Min Act: -0.1700
Data Index: 6375742 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.4967. Min Range: -2.4967
Max Act: 2.4642. Min Act: -0.1700
Data Index: 6715435 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.4967. Min Range: -2.4967
Max Act: 2.4642. Min Act: -0.1700
Data Index: 3104919 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.4967. Min Range: -2.4967
Max Act: 2.4480. Min Act: -0.1700
Data Index: 442649 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.4967. Min Range: -2.4967
Max Act: 2.4480. Min Act: -0.1700
Data Index: 5185767 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.4967. Min Range: -2.4967
Max Act: 2.4480. Min Act: -0.1700
Data Index: 293110 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.4967. Min Range: -2.4967
Max Act: 2.4480. Min Act: -0.1700
Data Index: 3014672 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.4967. Min Range: -2.4967
Max Act: 2.4317. Min Act: -0.1700
Data Index: 1853821 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.4967. Min Range: -2.4967
Max Act: 2.4317. Min Act: -0.1700
Data Index: 6017135 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.4967. Min Range: -2.4967
Max Act: 2.4317. Min Act: -0.1700
Data Index: 7420116 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.4967. Min Range: -2.4967
Max Act: 2.4317. Min Act: -0.1700
Data Index: 3390991 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.4967. Min Range: -2.4967
Max Act: 2.4317. Min Act: -0.1700
Data Index: 5136376 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.4967. Min Range: -2.4967
Max Act: 2.4154. Min Act: -0.1700
Data Index: 8734960 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.4967. Min Range: -2.4967
Max Act: 2.4317. Min Act: -0.1700
Data Index: 8320221 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.4967. Min Range: -2.4967
Max Act: 2.4317. Min Act: -0.1700
Data Index: 2359036 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.4967. Min Range: -2.4967
Max Act: 2.3991. Min Act: -0.1700
Data Index: 358448 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.4967. Min Range: -2.4967
Max Act: 2.4154. Min Act: -0.1700
Data Index: 760466 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.4967. Min Range: -2.4967
Max Act: 2.4154. Min Act: -0.1700
Data Index: 4048491 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.4967. Min Range: -2.4967
Max Act: 2.4154. Min Act: -0.1700
Data Index: 8008965 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #19