Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6019 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6619. Min Range: -4.6619
Max Act: 4.6619. Min Act: -0.1700
Data Index: 5423835 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6619. Min Range: -4.6619
Max Act: 4.3806. Min Act: -0.1700
Data Index: 1956386 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6619. Min Range: -4.6619
Max Act: 4.3494. Min Act: -0.1700
Data Index: 6541515 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6619. Min Range: -4.6619
Max Act: 4.2869. Min Act: -0.1700
Data Index: 8638905 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6619. Min Range: -4.6619
Max Act: 4.2556. Min Act: -0.1700
Data Index: 168761 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6619. Min Range: -4.6619
Max Act: 4.2244. Min Act: -0.1700
Data Index: 1568227 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6619. Min Range: -4.6619
Max Act: 4.2244. Min Act: -0.1700
Data Index: 734475 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6619. Min Range: -4.6619
Max Act: 4.1931. Min Act: -0.1700
Data Index: 4928835 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6619. Min Range: -4.6619
Max Act: 4.1931. Min Act: -0.1700
Data Index: 465061 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6619. Min Range: -4.6619
Max Act: 4.1931. Min Act: -0.1700
Data Index: 3452291 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6619. Min Range: -4.6619
Max Act: 4.1306. Min Act: -0.1700
Data Index: 43591 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6619. Min Range: -4.6619
Max Act: 4.1306. Min Act: -0.1700
Data Index: 8032714 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6619. Min Range: -4.6619
Max Act: 4.0993. Min Act: -0.1700
Data Index: 8657714 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6619. Min Range: -4.6619
Max Act: 4.0993. Min Act: -0.1700
Data Index: 6114220 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6619. Min Range: -4.6619
Max Act: 4.0993. Min Act: -0.1700
Data Index: 8418562 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6619. Min Range: -4.6619
Max Act: 4.0993. Min Act: -0.1700
Data Index: 4707363 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6619. Min Range: -4.6619
Max Act: 4.0993. Min Act: -0.1700
Data Index: 8301750 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6619. Min Range: -4.6619
Max Act: 4.0993. Min Act: -0.1700
Data Index: 1985557 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6619. Min Range: -4.6619
Max Act: 4.0993. Min Act: -0.1700
Data Index: 4422581 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6619. Min Range: -4.6619
Max Act: 4.0681. Min Act: -0.1700
Data Index: 5818322 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #19