Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4974 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4865. Min Range: -7.4865
Max Act: 7.4865. Min Act: -0.1700
Data Index: 6193382 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4865. Min Range: -7.4865
Max Act: 7.1115. Min Act: -0.1700
Data Index: 4452222 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4865. Min Range: -7.4865
Max Act: 7.0490. Min Act: -0.1700
Data Index: 7761917 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4865. Min Range: -7.4865
Max Act: 6.9240. Min Act: -0.1700
Data Index: 114927 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4865. Min Range: -7.4865
Max Act: 6.8927. Min Act: -0.1700
Data Index: 1339569 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4865. Min Range: -7.4865
Max Act: 6.8615. Min Act: -0.1700
Data Index: 3811529 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4865. Min Range: -7.4865
Max Act: 6.8302. Min Act: -0.1700
Data Index: 1269505 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4865. Min Range: -7.4865
Max Act: 6.7677. Min Act: -0.1700
Data Index: 2378193 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4865. Min Range: -7.4865
Max Act: 6.7990. Min Act: -0.1700
Data Index: 3358687 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4865. Min Range: -7.4865
Max Act: 6.7365. Min Act: -0.1700
Data Index: 1747548 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4865. Min Range: -7.4865
Max Act: 6.7365. Min Act: -0.1700
Data Index: 6999094 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4865. Min Range: -7.4865
Max Act: 6.7052. Min Act: -0.1700
Data Index: 5423648 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4865. Min Range: -7.4865
Max Act: 6.7052. Min Act: -0.1700
Data Index: 1768543 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4865. Min Range: -7.4865
Max Act: 6.7052. Min Act: -0.1700
Data Index: 8526350 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4865. Min Range: -7.4865
Max Act: 6.6740. Min Act: -0.1700
Data Index: 3902874 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4865. Min Range: -7.4865
Max Act: 6.6740. Min Act: -0.1700
Data Index: 7858350 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4865. Min Range: -7.4865
Max Act: 6.6740. Min Act: -0.1700
Data Index: 7835455 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4865. Min Range: -7.4865
Max Act: 6.6115. Min Act: -0.1700
Data Index: 7386255 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4865. Min Range: -7.4865
Max Act: 6.6115. Min Act: -0.1700
Data Index: 2859901 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4865. Min Range: -7.4865
Max Act: 6.6115. Min Act: -0.1700
Data Index: 4370834 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #19