Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1977 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7769. Min Range: -2.7769
Max Act: 2.7769. Min Act: -0.1700
Data Index: 2209087 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7769. Min Range: -2.7769
Max Act: 2.7130. Min Act: -0.1700
Data Index: 7396515 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7769. Min Range: -2.7769
Max Act: 2.7290. Min Act: -0.1700
Data Index: 5647619 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7769. Min Range: -2.7769
Max Act: 2.7450. Min Act: -0.1700
Data Index: 5705317 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7769. Min Range: -2.7769
Max Act: 2.7130. Min Act: -0.1700
Data Index: 6858843 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7769. Min Range: -2.7769
Max Act: 2.7130. Min Act: -0.1700
Data Index: 6682061 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7769. Min Range: -2.7769
Max Act: 2.6810. Min Act: -0.1700
Data Index: 4634845 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7769. Min Range: -2.7769
Max Act: 2.7130. Min Act: -0.1700
Data Index: 7971801 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7769. Min Range: -2.7769
Max Act: 2.7130. Min Act: -0.1700
Data Index: 4896712 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7769. Min Range: -2.7769
Max Act: 2.6970. Min Act: -0.1700
Data Index: 6987973 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7769. Min Range: -2.7769
Max Act: 2.6970. Min Act: -0.1700
Data Index: 3689256 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7769. Min Range: -2.7769
Max Act: 2.6810. Min Act: -0.1700
Data Index: 2410162 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7769. Min Range: -2.7769
Max Act: 2.6810. Min Act: -0.1700
Data Index: 4674812 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7769. Min Range: -2.7769
Max Act: 2.6489. Min Act: -0.1700
Data Index: 6682059 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7769. Min Range: -2.7769
Max Act: 2.6650. Min Act: -0.1700
Data Index: 3789588 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7769. Min Range: -2.7769
Max Act: 2.6810. Min Act: -0.1700
Data Index: 4099348 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7769. Min Range: -2.7769
Max Act: 2.6810. Min Act: -0.1700
Data Index: 906659 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7769. Min Range: -2.7769
Max Act: 2.6650. Min Act: -0.1700
Data Index: 2568391 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7769. Min Range: -2.7769
Max Act: 2.6489. Min Act: -0.1700
Data Index: 4602793 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7769. Min Range: -2.7769
Max Act: 2.6810. Min Act: -0.1700
Data Index: 3451644 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #19