Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3193 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3961. Min Range: -5.3961
Max Act: 5.3961. Min Act: -0.1700
Data Index: 6822713 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3961. Min Range: -5.3961
Max Act: 5.3336. Min Act: -0.1700
Data Index: 5423385 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3961. Min Range: -5.3961
Max Act: 5.2399. Min Act: -0.1700
Data Index: 782259 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3961. Min Range: -5.3961
Max Act: 5.2711. Min Act: -0.1700
Data Index: 3969917 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3961. Min Range: -5.3961
Max Act: 5.2399. Min Act: -0.1700
Data Index: 2726036 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3961. Min Range: -5.3961
Max Act: 5.2399. Min Act: -0.1700
Data Index: 7729586 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3961. Min Range: -5.3961
Max Act: 5.2399. Min Act: -0.1700
Data Index: 6351700 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3961. Min Range: -5.3961
Max Act: 5.1461. Min Act: -0.1700
Data Index: 3048925 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3961. Min Range: -5.3961
Max Act: 5.1774. Min Act: -0.1700
Data Index: 4989214 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3961. Min Range: -5.3961
Max Act: 5.1461. Min Act: -0.1700
Data Index: 750936 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3961. Min Range: -5.3961
Max Act: 5.1461. Min Act: -0.1700
Data Index: 5272436 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3961. Min Range: -5.3961
Max Act: 5.1461. Min Act: -0.1700
Data Index: 7629123 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3961. Min Range: -5.3961
Max Act: 5.1461. Min Act: -0.1700
Data Index: 1807606 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3961. Min Range: -5.3961
Max Act: 5.1149. Min Act: -0.1700
Data Index: 4725963 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3961. Min Range: -5.3961
Max Act: 5.0836. Min Act: -0.1700
Data Index: 7070427 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3961. Min Range: -5.3961
Max Act: 5.1149. Min Act: -0.1700
Data Index: 8230981 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3961. Min Range: -5.3961
Max Act: 5.0524. Min Act: -0.1700
Data Index: 801082 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3961. Min Range: -5.3961
Max Act: 5.0524. Min Act: -0.1700
Data Index: 5975144 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3961. Min Range: -5.3961
Max Act: 5.0211. Min Act: -0.1700
Data Index: 5657577 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3961. Min Range: -5.3961
Max Act: 4.9899. Min Act: -0.1700
Data Index: 6096837 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19