Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4233 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7106. Min Range: -2.7106
Max Act: 2.7106. Min Act: -0.1700
Data Index: 3577560 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7106. Min Range: -2.7106
Max Act: 2.6946. Min Act: -0.1700
Data Index: 660184 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7106. Min Range: -2.7106
Max Act: 2.6786. Min Act: -0.1700
Data Index: 198350 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7106. Min Range: -2.7106
Max Act: 2.6625. Min Act: -0.1700
Data Index: 3119589 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7106. Min Range: -2.7106
Max Act: 2.5983. Min Act: -0.1700
Data Index: 4275615 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7106. Min Range: -2.7106
Max Act: 2.5983. Min Act: -0.1700
Data Index: 4999980 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7106. Min Range: -2.7106
Max Act: 2.5983. Min Act: -0.1700
Data Index: 7946070 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7106. Min Range: -2.7106
Max Act: 2.5983. Min Act: -0.1700
Data Index: 6534878 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7106. Min Range: -2.7106
Max Act: 2.5822. Min Act: -0.1700
Data Index: 6761226 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7106. Min Range: -2.7106
Max Act: 2.5822. Min Act: -0.1700
Data Index: 5338075 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7106. Min Range: -2.7106
Max Act: 2.5822. Min Act: -0.1698
Data Index: 3084726 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7106. Min Range: -2.7106
Max Act: 2.5499. Min Act: -0.1700
Data Index: 4152196 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7106. Min Range: -2.7106
Max Act: 2.5661. Min Act: -0.1700
Data Index: 3831849 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7106. Min Range: -2.7106
Max Act: 2.5499. Min Act: -0.1700
Data Index: 2933331 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7106. Min Range: -2.7106
Max Act: 2.5499. Min Act: -0.1700
Data Index: 1693365 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7106. Min Range: -2.7106
Max Act: 2.5338. Min Act: -0.1700
Data Index: 3054457 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7106. Min Range: -2.7106
Max Act: 2.5499. Min Act: -0.1700
Data Index: 997924 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7106. Min Range: -2.7106
Max Act: 2.5338. Min Act: -0.1700
Data Index: 1463860 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7106. Min Range: -2.7106
Max Act: 2.5499. Min Act: -0.1700
Data Index: 5577396 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7106. Min Range: -2.7106
Max Act: 2.5176. Min Act: -0.1700
Data Index: 6297403 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #19