Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4595 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6008. Min Range: -5.6008
Max Act: 5.6008. Min Act: -0.1700
Data Index: 3888138 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6008. Min Range: -5.6008
Max Act: 5.3820. Min Act: -0.1700
Data Index: 1874846 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6008. Min Range: -5.6008
Max Act: 5.3508. Min Act: -0.1700
Data Index: 4415176 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6008. Min Range: -5.6008
Max Act: 5.2570. Min Act: -0.1700
Data Index: 4523227 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6008. Min Range: -5.6008
Max Act: 5.1320. Min Act: -0.1700
Data Index: 3176401 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6008. Min Range: -5.6008
Max Act: 5.0383. Min Act: -0.1700
Data Index: 2412388 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6008. Min Range: -5.6008
Max Act: 5.0070. Min Act: -0.1700
Data Index: 2444255 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6008. Min Range: -5.6008
Max Act: 5.0070. Min Act: -0.1700
Data Index: 7360903 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6008. Min Range: -5.6008
Max Act: 4.9758. Min Act: -0.1700
Data Index: 4959135 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6008. Min Range: -5.6008
Max Act: 5.0070. Min Act: -0.1700
Data Index: 3326944 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6008. Min Range: -5.6008
Max Act: 4.9445. Min Act: -0.1700
Data Index: 6538806 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6008. Min Range: -5.6008
Max Act: 4.9445. Min Act: -0.1700
Data Index: 8107208 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6008. Min Range: -5.6008
Max Act: 4.9445. Min Act: -0.1700
Data Index: 6865745 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6008. Min Range: -5.6008
Max Act: 4.9758. Min Act: -0.1700
Data Index: 8189242 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6008. Min Range: -5.6008
Max Act: 4.9445. Min Act: -0.1700
Data Index: 511595 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6008. Min Range: -5.6008
Max Act: 4.9758. Min Act: -0.1700
Data Index: 398186 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6008. Min Range: -5.6008
Max Act: 4.9445. Min Act: -0.1700
Data Index: 7318491 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6008. Min Range: -5.6008
Max Act: 4.9133. Min Act: -0.1700
Data Index: 1790612 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6008. Min Range: -5.6008
Max Act: 4.9133. Min Act: -0.1700
Data Index: 3154401 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6008. Min Range: -5.6008
Max Act: 4.9133. Min Act: -0.1700
Data Index: 5500684 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #19