Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6179 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3113. Min Range: -6.3113
Max Act: 6.3113. Min Act: -0.1700
Data Index: 2328644 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3113. Min Range: -6.3113
Max Act: 6.2488. Min Act: -0.1700
Data Index: 5202823 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3113. Min Range: -6.3113
Max Act: 6.0925. Min Act: -0.1700
Data Index: 3883319 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3113. Min Range: -6.3113
Max Act: 5.9988. Min Act: -0.1700
Data Index: 6445820 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3113. Min Range: -6.3113
Max Act: 5.9675. Min Act: -0.1700
Data Index: 3536973 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3113. Min Range: -6.3113
Max Act: 5.9050. Min Act: -0.1700
Data Index: 7265145 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3113. Min Range: -6.3113
Max Act: 5.9050. Min Act: -0.1700
Data Index: 3709734 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3113. Min Range: -6.3113
Max Act: 5.8738. Min Act: -0.1700
Data Index: 4308323 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3113. Min Range: -6.3113
Max Act: 5.8738. Min Act: -0.1700
Data Index: 5183927 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3113. Min Range: -6.3113
Max Act: 5.8425. Min Act: -0.1700
Data Index: 5176180 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3113. Min Range: -6.3113
Max Act: 5.8113. Min Act: -0.1700
Data Index: 3113727 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3113. Min Range: -6.3113
Max Act: 5.8113. Min Act: -0.1700
Data Index: 5751042 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3113. Min Range: -6.3113
Max Act: 5.8113. Min Act: -0.1700
Data Index: 5796260 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3113. Min Range: -6.3113
Max Act: 5.7488. Min Act: -0.1700
Data Index: 8185847 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3113. Min Range: -6.3113
Max Act: 5.7800. Min Act: -0.1700
Data Index: 1180827 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3113. Min Range: -6.3113
Max Act: 5.7175. Min Act: -0.1700
Data Index: 3317319 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3113. Min Range: -6.3113
Max Act: 5.7175. Min Act: -0.1700
Data Index: 2545149 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3113. Min Range: -6.3113
Max Act: 5.6550. Min Act: -0.1700
Data Index: 7562004 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3113. Min Range: -6.3113
Max Act: 5.6550. Min Act: -0.1700
Data Index: 3239196 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3113. Min Range: -6.3113
Max Act: 5.6550. Min Act: -0.1700
Data Index: 6699978 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #19