Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2704 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4101. Min Range: -7.4101
Max Act: 7.4101. Min Act: -0.1700
Data Index: 2111994 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4101. Min Range: -7.4101
Max Act: 7.3476. Min Act: -0.1700
Data Index: 1918314 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4101. Min Range: -7.4101
Max Act: 7.3788. Min Act: -0.1700
Data Index: 4552649 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4101. Min Range: -7.4101
Max Act: 7.3163. Min Act: -0.1700
Data Index: 8605091 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4101. Min Range: -7.4101
Max Act: 7.3163. Min Act: -0.1700
Data Index: 2158165 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4101. Min Range: -7.4101
Max Act: 7.3476. Min Act: -0.1700
Data Index: 5810814 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4101. Min Range: -7.4101
Max Act: 7.2851. Min Act: -0.1700
Data Index: 2345130 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4101. Min Range: -7.4101
Max Act: 7.1913. Min Act: -0.1700
Data Index: 3628589 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4101. Min Range: -7.4101
Max Act: 7.0976. Min Act: -0.1700
Data Index: 4256869 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4101. Min Range: -7.4101
Max Act: 7.0976. Min Act: -0.1700
Data Index: 5754913 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4101. Min Range: -7.4101
Max Act: 7.0663. Min Act: -0.1700
Data Index: 4953325 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4101. Min Range: -7.4101
Max Act: 7.0663. Min Act: -0.1700
Data Index: 3543869 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4101. Min Range: -7.4101
Max Act: 7.0663. Min Act: -0.1700
Data Index: 7183572 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4101. Min Range: -7.4101
Max Act: 7.0038. Min Act: -0.1700
Data Index: 3050211 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4101. Min Range: -7.4101
Max Act: 7.0038. Min Act: -0.1700
Data Index: 4228819 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4101. Min Range: -7.4101
Max Act: 6.9101. Min Act: -0.1700
Data Index: 4885279 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4101. Min Range: -7.4101
Max Act: 6.9726. Min Act: -0.1700
Data Index: 2945304 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4101. Min Range: -7.4101
Max Act: 6.9101. Min Act: -0.1700
Data Index: 5173159 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4101. Min Range: -7.4101
Max Act: 6.8476. Min Act: -0.1700
Data Index: 3212156 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4101. Min Range: -7.4101
Max Act: 6.8788. Min Act: -0.1700
Data Index: 326238 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #19