Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3701 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.3481. Min Act: -0.1700
Data Index: 996833 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.3168. Min Act: -0.1700
Data Index: 7267445 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.2856. Min Act: -0.1700
Data Index: 4063972 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.3168. Min Act: -0.1700
Data Index: 7636663 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.2543. Min Act: -0.1700
Data Index: 7998336 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.1918. Min Act: -0.1700
Data Index: 4242759 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.1606. Min Act: -0.1700
Data Index: 4171302 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.1606. Min Act: -0.1700
Data Index: 3972233 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.1606. Min Act: -0.1700
Data Index: 4508332 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.1606. Min Act: -0.1700
Data Index: 3216210 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.1293. Min Act: -0.1700
Data Index: 3074812 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.0981. Min Act: -0.1700
Data Index: 8271977 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.0981. Min Act: -0.1700
Data Index: 6839980 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.0981. Min Act: -0.1700
Data Index: 5686429 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.0668. Min Act: -0.1700
Data Index: 444460 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.0356. Min Act: -0.1700
Data Index: 6380540 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.0668. Min Act: -0.1700
Data Index: 7226147 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.0668. Min Act: -0.1700
Data Index: 2050995 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.0668. Min Act: -0.1700
Data Index: 5320586 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3481. Min Range: -5.3481
Max Act: 5.0356. Min Act: -0.1700
Data Index: 4342480 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #19