Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 1711 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 8.9893. Min Range: -8.9893
Max Act: 8.9893. Min Act: -0.1699
Data Index: 78294 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9893. Min Range: -8.9893
Max Act: 8.6143. Min Act: -0.1700
Data Index: 7747299 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9893. Min Range: -8.9893
Max Act: 8.2393. Min Act: -0.1698
Data Index: 5173955 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9893. Min Range: -8.9893
Max Act: 8.3018. Min Act: -0.1700
Data Index: 6359268 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9893. Min Range: -8.9893
Max Act: 8.1768. Min Act: -0.1700
Data Index: 5388789 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9893. Min Range: -8.9893
Max Act: 8.1143. Min Act: -0.1699
Data Index: 3564254 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9893. Min Range: -8.9893
Max Act: 8.1143. Min Act: -0.1700
Data Index: 3564253 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9893. Min Range: -8.9893
Max Act: 7.9268. Min Act: -0.1700
Data Index: 6911794 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9893. Min Range: -8.9893
Max Act: 7.9893. Min Act: -0.1700
Data Index: 2853656 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9893. Min Range: -8.9893
Max Act: 7.8018. Min Act: -0.1700
Data Index: 43335 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9893. Min Range: -8.9893
Max Act: 7.8018. Min Act: -0.1700
Data Index: 1972279 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9893. Min Range: -8.9893
Max Act: 7.7393. Min Act: -0.1700
Data Index: 7420590 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9893. Min Range: -8.9893
Max Act: 7.6143. Min Act: -0.1700
Data Index: 5675901 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9893. Min Range: -8.9893
Max Act: 7.7393. Min Act: -0.1700
Data Index: 5733978 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9893. Min Range: -8.9893
Max Act: 7.6143. Min Act: -0.1700
Data Index: 96395 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9893. Min Range: -8.9893
Max Act: 7.6768. Min Act: -0.1700
Data Index: 7470599 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9893. Min Range: -8.9893
Max Act: 7.6143. Min Act: -0.1700
Data Index: 3040176 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9893. Min Range: -8.9893
Max Act: 7.6143. Min Act: -0.1700
Data Index: 5939476 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9893. Min Range: -8.9893
Max Act: 7.4268. Min Act: -0.1700
Data Index: 6657539 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9893. Min Range: -8.9893
Max Act: 7.8018. Min Act: -0.1700
Data Index: 6630249 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #19