Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3399 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1552. Min Range: -6.1552
Max Act: 6.1552. Min Act: -0.1700
Data Index: 6545586 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1552. Min Range: -6.1552
Max Act: 5.8114. Min Act: -0.1700
Data Index: 7239286 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1552. Min Range: -6.1552
Max Act: 5.8114. Min Act: -0.1700
Data Index: 5340646 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1552. Min Range: -6.1552
Max Act: 5.7489. Min Act: -0.1700
Data Index: 2962623 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1552. Min Range: -6.1552
Max Act: 5.7489. Min Act: -0.1700
Data Index: 833401 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1552. Min Range: -6.1552
Max Act: 5.7802. Min Act: -0.1700
Data Index: 5640577 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1552. Min Range: -6.1552
Max Act: 5.7177. Min Act: -0.1700
Data Index: 2274480 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1552. Min Range: -6.1552
Max Act: 5.7177. Min Act: -0.1700
Data Index: 6964462 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1552. Min Range: -6.1552
Max Act: 5.7177. Min Act: -0.1700
Data Index: 7768020 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1552. Min Range: -6.1552
Max Act: 5.6864. Min Act: -0.1700
Data Index: 687300 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1552. Min Range: -6.1552
Max Act: 5.6552. Min Act: -0.1700
Data Index: 8278158 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1552. Min Range: -6.1552
Max Act: 5.6239. Min Act: -0.1700
Data Index: 8747264 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1552. Min Range: -6.1552
Max Act: 5.5614. Min Act: -0.1700
Data Index: 546908 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1552. Min Range: -6.1552
Max Act: 5.5927. Min Act: -0.1700
Data Index: 7349103 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1552. Min Range: -6.1552
Max Act: 5.5927. Min Act: -0.1700
Data Index: 8615292 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1552. Min Range: -6.1552
Max Act: 5.5614. Min Act: -0.1700
Data Index: 946236 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1552. Min Range: -6.1552
Max Act: 5.5302. Min Act: -0.1700
Data Index: 5116295 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1552. Min Range: -6.1552
Max Act: 5.5302. Min Act: -0.1700
Data Index: 6060978 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1552. Min Range: -6.1552
Max Act: 5.4989. Min Act: -0.1700
Data Index: 7262282 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1552. Min Range: -6.1552
Max Act: 5.4989. Min Act: -0.1700
Data Index: 8180941 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #19