Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2973 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6911. Min Range: -3.6911
Max Act: 3.6911. Min Act: -0.1700
Data Index: 8234246 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6911. Min Range: -3.6911
Max Act: 3.6598. Min Act: -0.1700
Data Index: 1144410 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6911. Min Range: -3.6911
Max Act: 3.6128. Min Act: -0.1700
Data Index: 5749444 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6911. Min Range: -3.6911
Max Act: 3.6128. Min Act: -0.1700
Data Index: 463252 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6911. Min Range: -3.6911
Max Act: 3.5815. Min Act: -0.1700
Data Index: 7201104 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6911. Min Range: -3.6911
Max Act: 3.4876. Min Act: -0.1700
Data Index: 8515513 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6911. Min Range: -3.6911
Max Act: 3.4719. Min Act: -0.1700
Data Index: 1137447 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6911. Min Range: -3.6911
Max Act: 3.4719. Min Act: -0.1700
Data Index: 5078077 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6911. Min Range: -3.6911
Max Act: 3.4563. Min Act: -0.1700
Data Index: 3354960 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6911. Min Range: -3.6911
Max Act: 3.4719. Min Act: -0.1700
Data Index: 4768273 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6911. Min Range: -3.6911
Max Act: 3.4719. Min Act: -0.1700
Data Index: 4520000 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6911. Min Range: -3.6911
Max Act: 3.4563. Min Act: -0.1700
Data Index: 4907501 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6911. Min Range: -3.6911
Max Act: 3.4406. Min Act: -0.1700
Data Index: 6758282 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6911. Min Range: -3.6911
Max Act: 3.4249. Min Act: -0.1700
Data Index: 2097807 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6911. Min Range: -3.6911
Max Act: 3.4563. Min Act: -0.1700
Data Index: 4816164 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6911. Min Range: -3.6911
Max Act: 3.4406. Min Act: -0.1700
Data Index: 7653192 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6911. Min Range: -3.6911
Max Act: 3.4249. Min Act: -0.1700
Data Index: 931162 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6911. Min Range: -3.6911
Max Act: 3.4249. Min Act: -0.1700
Data Index: 1279040 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6911. Min Range: -3.6911
Max Act: 3.4092. Min Act: -0.1700
Data Index: 7399176 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6911. Min Range: -3.6911
Max Act: 3.4092. Min Act: -0.1700
Data Index: 6776919 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #19