Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1745 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0162. Min Range: -6.0162
Max Act: 5.9850. Min Act: -0.1700
Data Index: 8818498 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0162. Min Range: -6.0162
Max Act: 6.0162. Min Act: -0.1700
Data Index: 7557157 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0162. Min Range: -6.0162
Max Act: 5.9850. Min Act: -0.1700
Data Index: 5032496 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0162. Min Range: -6.0162
Max Act: 5.9850. Min Act: -0.1700
Data Index: 2219095 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0162. Min Range: -6.0162
Max Act: 5.9537. Min Act: -0.1700
Data Index: 2962177 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0162. Min Range: -6.0162
Max Act: 5.9537. Min Act: -0.1700
Data Index: 2970351 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0162. Min Range: -6.0162
Max Act: 5.9225. Min Act: -0.1700
Data Index: 5694673 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0162. Min Range: -6.0162
Max Act: 5.8912. Min Act: -0.1700
Data Index: 8300066 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0162. Min Range: -6.0162
Max Act: 5.8287. Min Act: -0.1700
Data Index: 5189673 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0162. Min Range: -6.0162
Max Act: 5.8287. Min Act: -0.1700
Data Index: 5021782 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0162. Min Range: -6.0162
Max Act: 5.7975. Min Act: -0.1700
Data Index: 7090453 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0162. Min Range: -6.0162
Max Act: 5.7975. Min Act: -0.1700
Data Index: 43990 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0162. Min Range: -6.0162
Max Act: 5.7662. Min Act: -0.1700
Data Index: 7979939 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0162. Min Range: -6.0162
Max Act: 5.7350. Min Act: -0.1700
Data Index: 8285751 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0162. Min Range: -6.0162
Max Act: 5.7662. Min Act: -0.1700
Data Index: 3359265 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0162. Min Range: -6.0162
Max Act: 5.7662. Min Act: -0.1700
Data Index: 4840009 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0162. Min Range: -6.0162
Max Act: 5.7662. Min Act: -0.1700
Data Index: 1191142 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0162. Min Range: -6.0162
Max Act: 5.7350. Min Act: -0.1700
Data Index: 8265868 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0162. Min Range: -6.0162
Max Act: 5.7350. Min Act: -0.1700
Data Index: 6553535 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0162. Min Range: -6.0162
Max Act: 5.7350. Min Act: -0.1700
Data Index: 460033 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19