Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3471 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2874. Min Range: -6.2874
Max Act: 6.2874. Min Act: -0.1700
Data Index: 2985203 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2874. Min Range: -6.2874
Max Act: 6.2874. Min Act: -0.1700
Data Index: 4260759 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2874. Min Range: -6.2874
Max Act: 6.2249. Min Act: -0.1700
Data Index: 6765210 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2874. Min Range: -6.2874
Max Act: 6.1937. Min Act: -0.1700
Data Index: 3190248 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2874. Min Range: -6.2874
Max Act: 6.1937. Min Act: -0.1700
Data Index: 4300715 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2874. Min Range: -6.2874
Max Act: 6.2249. Min Act: -0.1700
Data Index: 3666715 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2874. Min Range: -6.2874
Max Act: 6.1624. Min Act: -0.1700
Data Index: 6491742 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2874. Min Range: -6.2874
Max Act: 6.1624. Min Act: -0.1700
Data Index: 6692875 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2874. Min Range: -6.2874
Max Act: 6.0999. Min Act: -0.1700
Data Index: 8807944 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2874. Min Range: -6.2874
Max Act: 6.0999. Min Act: -0.1700
Data Index: 6941372 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2874. Min Range: -6.2874
Max Act: 6.1312. Min Act: -0.1700
Data Index: 3663387 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2874. Min Range: -6.2874
Max Act: 6.0687. Min Act: -0.1700
Data Index: 3996206 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2874. Min Range: -6.2874
Max Act: 6.1312. Min Act: -0.1700
Data Index: 4303065 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2874. Min Range: -6.2874
Max Act: 6.0999. Min Act: -0.1700
Data Index: 4798139 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2874. Min Range: -6.2874
Max Act: 6.0999. Min Act: -0.1700
Data Index: 5969641 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2874. Min Range: -6.2874
Max Act: 6.0687. Min Act: -0.1700
Data Index: 2064513 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2874. Min Range: -6.2874
Max Act: 6.0374. Min Act: -0.1700
Data Index: 1837495 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2874. Min Range: -6.2874
Max Act: 6.0687. Min Act: -0.1700
Data Index: 2249090 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2874. Min Range: -6.2874
Max Act: 6.0687. Min Act: -0.1700
Data Index: 3024249 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2874. Min Range: -6.2874
Max Act: 6.0374. Min Act: -0.1700
Data Index: 3224492 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #19