Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4145 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7645. Min Range: -5.7645
Max Act: 5.7645. Min Act: -0.1700
Data Index: 637193 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7645. Min Range: -5.7645
Max Act: 5.6708. Min Act: -0.1700
Data Index: 5544868 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7645. Min Range: -5.7645
Max Act: 5.6708. Min Act: -0.1700
Data Index: 7179198 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7645. Min Range: -5.7645
Max Act: 5.6395. Min Act: -0.1700
Data Index: 7188287 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7645. Min Range: -5.7645
Max Act: 5.7020. Min Act: -0.1700
Data Index: 5464894 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7645. Min Range: -5.7645
Max Act: 5.6708. Min Act: -0.1700
Data Index: 3162189 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7645. Min Range: -5.7645
Max Act: 5.6395. Min Act: -0.1700
Data Index: 8285783 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7645. Min Range: -5.7645
Max Act: 5.6395. Min Act: -0.1700
Data Index: 203720 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7645. Min Range: -5.7645
Max Act: 5.6708. Min Act: -0.1700
Data Index: 7306853 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7645. Min Range: -5.7645
Max Act: 5.6395. Min Act: -0.1700
Data Index: 3141634 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7645. Min Range: -5.7645
Max Act: 5.6083. Min Act: -0.1700
Data Index: 2704743 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7645. Min Range: -5.7645
Max Act: 5.6083. Min Act: -0.1700
Data Index: 203710 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7645. Min Range: -5.7645
Max Act: 5.5770. Min Act: -0.1700
Data Index: 8520530 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7645. Min Range: -5.7645
Max Act: 5.5770. Min Act: -0.1700
Data Index: 3547413 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7645. Min Range: -5.7645
Max Act: 5.5770. Min Act: -0.1700
Data Index: 6281973 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7645. Min Range: -5.7645
Max Act: 5.5770. Min Act: -0.1700
Data Index: 4336586 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7645. Min Range: -5.7645
Max Act: 5.5770. Min Act: -0.1700
Data Index: 6846394 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7645. Min Range: -5.7645
Max Act: 5.5458. Min Act: -0.1700
Data Index: 7188286 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7645. Min Range: -5.7645
Max Act: 5.5458. Min Act: -0.1700
Data Index: 497381 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7645. Min Range: -5.7645
Max Act: 5.5458. Min Act: -0.1700
Data Index: 8215045 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #19