Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1833 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.4651. Min Range: -7.4651
Max Act: 7.4651. Min Act: -0.1700
Data Index: 4859477 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4651. Min Range: -7.4651
Max Act: 7.3713. Min Act: -0.1700
Data Index: 5061356 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4651. Min Range: -7.4651
Max Act: 7.2151. Min Act: -0.1700
Data Index: 1000370 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4651. Min Range: -7.4651
Max Act: 7.1838. Min Act: -0.1700
Data Index: 1734664 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4651. Min Range: -7.4651
Max Act: 7.1838. Min Act: -0.1700
Data Index: 6417099 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4651. Min Range: -7.4651
Max Act: 7.0901. Min Act: -0.1700
Data Index: 3585962 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4651. Min Range: -7.4651
Max Act: 7.0588. Min Act: -0.1700
Data Index: 4691004 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4651. Min Range: -7.4651
Max Act: 7.0276. Min Act: -0.1700
Data Index: 7197803 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4651. Min Range: -7.4651
Max Act: 6.9651. Min Act: -0.1700
Data Index: 6881550 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4651. Min Range: -7.4651
Max Act: 6.9651. Min Act: -0.1700
Data Index: 2552019 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4651. Min Range: -7.4651
Max Act: 6.9963. Min Act: -0.1700
Data Index: 5060728 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4651. Min Range: -7.4651
Max Act: 6.9651. Min Act: -0.1700
Data Index: 4562433 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4651. Min Range: -7.4651
Max Act: 6.9651. Min Act: -0.1700
Data Index: 3899541 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4651. Min Range: -7.4651
Max Act: 6.9026. Min Act: -0.1700
Data Index: 2851492 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4651. Min Range: -7.4651
Max Act: 6.9338. Min Act: -0.1700
Data Index: 4002453 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4651. Min Range: -7.4651
Max Act: 6.9026. Min Act: -0.1700
Data Index: 1628167 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4651. Min Range: -7.4651
Max Act: 6.9026. Min Act: -0.1700
Data Index: 5856898 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4651. Min Range: -7.4651
Max Act: 6.9026. Min Act: -0.1700
Data Index: 2449178 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4651. Min Range: -7.4651
Max Act: 6.8713. Min Act: -0.1700
Data Index: 7086387 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4651. Min Range: -7.4651
Max Act: 6.8713. Min Act: -0.1700
Data Index: 4427056 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #19