Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2866 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 2.0702. Min Range: -2.0702
Max Act: 2.0702. Min Act: -0.1700
Data Index: 5405273 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.0702. Min Range: -2.0702
Max Act: 2.0366. Min Act: -0.1700
Data Index: 4921624 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.0702. Min Range: -2.0702
Max Act: 2.0197. Min Act: -0.1700
Data Index: 8058772 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.0702. Min Range: -2.0702
Max Act: 2.0197. Min Act: -0.1700
Data Index: 1363452 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.0702. Min Range: -2.0702
Max Act: 2.0197. Min Act: -0.1700
Data Index: 3758520 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.0702. Min Range: -2.0702
Max Act: 2.0028. Min Act: -0.1700
Data Index: 1591189 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.0702. Min Range: -2.0702
Max Act: 1.9859. Min Act: -0.1700
Data Index: 6587648 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.0702. Min Range: -2.0702
Max Act: 1.9690. Min Act: -0.1700
Data Index: 648551 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.0702. Min Range: -2.0702
Max Act: 1.9690. Min Act: -0.1700
Data Index: 7222403 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.0702. Min Range: -2.0702
Max Act: 1.9859. Min Act: -0.1700
Data Index: 1545961 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.0702. Min Range: -2.0702
Max Act: 1.9690. Min Act: -0.1700
Data Index: 1747920 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.0702. Min Range: -2.0702
Max Act: 1.9859. Min Act: -0.1700
Data Index: 204611 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.0702. Min Range: -2.0702
Max Act: 1.9859. Min Act: -0.1700
Data Index: 8713930 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.0702. Min Range: -2.0702
Max Act: 1.9690. Min Act: -0.1700
Data Index: 6288838 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.0702. Min Range: -2.0702
Max Act: 1.9690. Min Act: -0.1700
Data Index: 5575751 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.0702. Min Range: -2.0702
Max Act: 1.9690. Min Act: -0.1700
Data Index: 3749621 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.0702. Min Range: -2.0702
Max Act: 1.9690. Min Act: -0.1700
Data Index: 589517 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.0702. Min Range: -2.0702
Max Act: 1.9350. Min Act: -0.1700
Data Index: 5798866 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.0702. Min Range: -2.0702
Max Act: 1.9520. Min Act: -0.1700
Data Index: 2056061 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.0702. Min Range: -2.0702
Max Act: 1.9690. Min Act: -0.1700
Data Index: 5218789 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #19