Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3009 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1382. Min Range: -6.1382
Max Act: 6.1382. Min Act: -0.1700
Data Index: 7159956 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1382. Min Range: -6.1382
Max Act: 6.0445. Min Act: -0.1700
Data Index: 7540929 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1382. Min Range: -6.1382
Max Act: 5.9820. Min Act: -0.1700
Data Index: 8658071 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1382. Min Range: -6.1382
Max Act: 5.9820. Min Act: -0.1700
Data Index: 4668163 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1382. Min Range: -6.1382
Max Act: 5.9195. Min Act: -0.1700
Data Index: 3275096 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1382. Min Range: -6.1382
Max Act: 5.9195. Min Act: -0.1700
Data Index: 5072598 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1382. Min Range: -6.1382
Max Act: 5.8882. Min Act: -0.1700
Data Index: 4945313 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1382. Min Range: -6.1382
Max Act: 5.8882. Min Act: -0.1700
Data Index: 7636098 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1382. Min Range: -6.1382
Max Act: 5.8882. Min Act: -0.1700
Data Index: 6938260 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1382. Min Range: -6.1382
Max Act: 5.8570. Min Act: -0.1700
Data Index: 3358303 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1382. Min Range: -6.1382
Max Act: 5.7632. Min Act: -0.1700
Data Index: 7150324 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1382. Min Range: -6.1382
Max Act: 5.7320. Min Act: -0.1700
Data Index: 6469638 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1382. Min Range: -6.1382
Max Act: 5.7320. Min Act: -0.1700
Data Index: 4428550 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1382. Min Range: -6.1382
Max Act: 5.6695. Min Act: -0.1700
Data Index: 6778806 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1382. Min Range: -6.1382
Max Act: 5.6695. Min Act: -0.1700
Data Index: 2733825 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1382. Min Range: -6.1382
Max Act: 5.6382. Min Act: -0.1700
Data Index: 873488 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1382. Min Range: -6.1382
Max Act: 5.6382. Min Act: -0.1700
Data Index: 4463436 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1382. Min Range: -6.1382
Max Act: 5.6382. Min Act: -0.1700
Data Index: 1721174 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1382. Min Range: -6.1382
Max Act: 5.6695. Min Act: -0.1700
Data Index: 5898124 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1382. Min Range: -6.1382
Max Act: 5.6382. Min Act: -0.1700
Data Index: 1757141 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19