Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3770 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9956. Min Range: -5.9956
Max Act: 5.9956. Min Act: -0.1700
Data Index: 3736781 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9956. Min Range: -5.9956
Max Act: 5.7456. Min Act: -0.1700
Data Index: 6194360 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9956. Min Range: -5.9956
Max Act: 5.5269. Min Act: -0.1700
Data Index: 7785468 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9956. Min Range: -5.9956
Max Act: 5.4644. Min Act: -0.1700
Data Index: 5481901 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9956. Min Range: -5.9956
Max Act: 5.4644. Min Act: -0.1700
Data Index: 8314306 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9956. Min Range: -5.9956
Max Act: 5.4331. Min Act: -0.1700
Data Index: 4767584 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9956. Min Range: -5.9956
Max Act: 5.4019. Min Act: -0.1700
Data Index: 2935320 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9956. Min Range: -5.9956
Max Act: 5.3706. Min Act: -0.1700
Data Index: 4529843 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9956. Min Range: -5.9956
Max Act: 5.3394. Min Act: -0.1700
Data Index: 2619171 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9956. Min Range: -5.9956
Max Act: 5.3394. Min Act: -0.1700
Data Index: 7430367 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9956. Min Range: -5.9956
Max Act: 5.3394. Min Act: -0.1700
Data Index: 4669033 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9956. Min Range: -5.9956
Max Act: 5.3394. Min Act: -0.1700
Data Index: 7284074 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9956. Min Range: -5.9956
Max Act: 5.2769. Min Act: -0.1700
Data Index: 7478107 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9956. Min Range: -5.9956
Max Act: 5.3081. Min Act: -0.1700
Data Index: 2359919 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9956. Min Range: -5.9956
Max Act: 5.3081. Min Act: -0.1700
Data Index: 4830459 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9956. Min Range: -5.9956
Max Act: 5.3081. Min Act: -0.1700
Data Index: 177730 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9956. Min Range: -5.9956
Max Act: 5.3394. Min Act: -0.1700
Data Index: 4997831 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9956. Min Range: -5.9956
Max Act: 5.3394. Min Act: -0.1700
Data Index: 115632 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9956. Min Range: -5.9956
Max Act: 5.3081. Min Act: -0.1700
Data Index: 1349419 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9956. Min Range: -5.9956
Max Act: 5.2769. Min Act: -0.1700
Data Index: 5363715 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #19