Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2124 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1082. Min Range: -8.1082
Max Act: 8.1082. Min Act: -0.1700
Data Index: 3824362 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1082. Min Range: -8.1082
Max Act: 8.0457. Min Act: -0.1700
Data Index: 121498 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1082. Min Range: -8.1082
Max Act: 7.8582. Min Act: -0.1700
Data Index: 2226613 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1082. Min Range: -8.1082
Max Act: 7.8582. Min Act: -0.1700
Data Index: 6329388 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1082. Min Range: -8.1082
Max Act: 7.7957. Min Act: -0.1700
Data Index: 5460016 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1082. Min Range: -8.1082
Max Act: 7.6082. Min Act: -0.1700
Data Index: 5518452 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1082. Min Range: -8.1082
Max Act: 7.6082. Min Act: -0.1700
Data Index: 1555804 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1082. Min Range: -8.1082
Max Act: 7.6082. Min Act: -0.1700
Data Index: 8255147 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1082. Min Range: -8.1082
Max Act: 7.6082. Min Act: -0.1700
Data Index: 3701086 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1082. Min Range: -8.1082
Max Act: 7.6082. Min Act: -0.1700
Data Index: 8715524 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1082. Min Range: -8.1082
Max Act: 7.5457. Min Act: -0.1700
Data Index: 4333297 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1082. Min Range: -8.1082
Max Act: 7.5144. Min Act: -0.1700
Data Index: 2552532 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1082. Min Range: -8.1082
Max Act: 7.5144. Min Act: -0.1700
Data Index: 3297541 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1082. Min Range: -8.1082
Max Act: 7.5144. Min Act: -0.1700
Data Index: 1640216 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1082. Min Range: -8.1082
Max Act: 7.5457. Min Act: -0.1700
Data Index: 4590665 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1082. Min Range: -8.1082
Max Act: 7.5144. Min Act: -0.1700
Data Index: 1857249 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1082. Min Range: -8.1082
Max Act: 7.4832. Min Act: -0.1700
Data Index: 4338194 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1082. Min Range: -8.1082
Max Act: 7.4832. Min Act: -0.1700
Data Index: 609010 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1082. Min Range: -8.1082
Max Act: 7.4832. Min Act: -0.1700
Data Index: 7747139 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1082. Min Range: -8.1082
Max Act: 7.4832. Min Act: -0.1700
Data Index: 7106015 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #19