Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3094 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7161. Min Range: -6.7161
Max Act: 6.7161. Min Act: -0.1700
Data Index: 8696515 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7161. Min Range: -6.7161
Max Act: 6.1536. Min Act: -0.1700
Data Index: 7869421 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7161. Min Range: -6.7161
Max Act: 6.0286. Min Act: -0.1700
Data Index: 2538964 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7161. Min Range: -6.7161
Max Act: 5.9974. Min Act: -0.1700
Data Index: 1658292 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7161. Min Range: -6.7161
Max Act: 5.9974. Min Act: -0.1700
Data Index: 5462739 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7161. Min Range: -6.7161
Max Act: 5.9036. Min Act: -0.1700
Data Index: 5718668 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7161. Min Range: -6.7161
Max Act: 5.8724. Min Act: -0.1700
Data Index: 5085954 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7161. Min Range: -6.7161
Max Act: 5.8724. Min Act: -0.1700
Data Index: 2665402 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7161. Min Range: -6.7161
Max Act: 5.8411. Min Act: -0.1700
Data Index: 2204579 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7161. Min Range: -6.7161
Max Act: 5.8099. Min Act: -0.1700
Data Index: 4600098 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7161. Min Range: -6.7161
Max Act: 5.8411. Min Act: -0.1700
Data Index: 8139028 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7161. Min Range: -6.7161
Max Act: 5.7474. Min Act: -0.1700
Data Index: 680095 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7161. Min Range: -6.7161
Max Act: 5.7474. Min Act: -0.1700
Data Index: 1978367 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7161. Min Range: -6.7161
Max Act: 5.7161. Min Act: -0.1700
Data Index: 4462806 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7161. Min Range: -6.7161
Max Act: 5.6849. Min Act: -0.1700
Data Index: 1603274 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7161. Min Range: -6.7161
Max Act: 5.7161. Min Act: -0.1700
Data Index: 855416 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7161. Min Range: -6.7161
Max Act: 5.6849. Min Act: -0.1700
Data Index: 5506668 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7161. Min Range: -6.7161
Max Act: 5.6536. Min Act: -0.1700
Data Index: 6023134 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7161. Min Range: -6.7161
Max Act: 5.6536. Min Act: -0.1700
Data Index: 4528342 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7161. Min Range: -6.7161
Max Act: 5.6536. Min Act: -0.1700
Data Index: 5534488 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #19