Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3239 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5762. Min Range: -9.5762
Max Act: 9.5762. Min Act: -0.1700
Data Index: 1522489 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5762. Min Range: -9.5762
Max Act: 9.2012. Min Act: -0.1700
Data Index: 310177 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5762. Min Range: -9.5762
Max Act: 9.1387. Min Act: -0.1700
Data Index: 7124949 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5762. Min Range: -9.5762
Max Act: 9.2012. Min Act: -0.1700
Data Index: 7118890 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5762. Min Range: -9.5762
Max Act: 9.0137. Min Act: -0.1700
Data Index: 4673589 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5762. Min Range: -9.5762
Max Act: 8.9512. Min Act: -0.1700
Data Index: 2452477 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5762. Min Range: -9.5762
Max Act: 8.9512. Min Act: -0.1700
Data Index: 6937267 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5762. Min Range: -9.5762
Max Act: 8.8887. Min Act: -0.1700
Data Index: 653594 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5762. Min Range: -9.5762
Max Act: 8.8262. Min Act: -0.1700
Data Index: 2287403 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5762. Min Range: -9.5762
Max Act: 8.8262. Min Act: -0.1700
Data Index: 822097 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5762. Min Range: -9.5762
Max Act: 8.8887. Min Act: -0.1700
Data Index: 5949086 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5762. Min Range: -9.5762
Max Act: 8.7637. Min Act: -0.1700
Data Index: 7160025 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5762. Min Range: -9.5762
Max Act: 8.8262. Min Act: -0.1700
Data Index: 7599110 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5762. Min Range: -9.5762
Max Act: 8.7637. Min Act: -0.1700
Data Index: 4426010 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5762. Min Range: -9.5762
Max Act: 8.7637. Min Act: -0.1700
Data Index: 1165766 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5762. Min Range: -9.5762
Max Act: 8.7012. Min Act: -0.1700
Data Index: 310176 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5762. Min Range: -9.5762
Max Act: 8.7012. Min Act: -0.1700
Data Index: 754712 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5762. Min Range: -9.5762
Max Act: 8.7012. Min Act: -0.1700
Data Index: 2798831 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5762. Min Range: -9.5762
Max Act: 8.7012. Min Act: -0.1700
Data Index: 2295915 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5762. Min Range: -9.5762
Max Act: 8.6387. Min Act: -0.1700
Data Index: 1183681 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #19