Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4115 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4548. Min Range: -5.4548
Max Act: 5.4548. Min Act: -0.1700
Data Index: 1017567 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4548. Min Range: -5.4548
Max Act: 5.1423. Min Act: -0.1700
Data Index: 2676722 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4548. Min Range: -5.4548
Max Act: 5.1110. Min Act: -0.1700
Data Index: 1105691 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4548. Min Range: -5.4548
Max Act: 5.0798. Min Act: -0.1700
Data Index: 3136712 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4548. Min Range: -5.4548
Max Act: 5.0485. Min Act: -0.1700
Data Index: 404131 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4548. Min Range: -5.4548
Max Act: 4.9860. Min Act: -0.1700
Data Index: 869520 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4548. Min Range: -5.4548
Max Act: 4.9548. Min Act: -0.1700
Data Index: 5156222 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4548. Min Range: -5.4548
Max Act: 4.9860. Min Act: -0.1700
Data Index: 4589377 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4548. Min Range: -5.4548
Max Act: 4.9548. Min Act: -0.1700
Data Index: 5953500 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4548. Min Range: -5.4548
Max Act: 4.9235. Min Act: -0.1700
Data Index: 7350551 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4548. Min Range: -5.4548
Max Act: 4.8610. Min Act: -0.1700
Data Index: 1742353 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4548. Min Range: -5.4548
Max Act: 4.8298. Min Act: -0.1700
Data Index: 1020245 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4548. Min Range: -5.4548
Max Act: 4.7673. Min Act: -0.1700
Data Index: 5264990 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4548. Min Range: -5.4548
Max Act: 4.7673. Min Act: -0.1700
Data Index: 4409957 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4548. Min Range: -5.4548
Max Act: 4.7673. Min Act: -0.1700
Data Index: 8246649 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4548. Min Range: -5.4548
Max Act: 4.7673. Min Act: -0.1700
Data Index: 1660871 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4548. Min Range: -5.4548
Max Act: 4.7048. Min Act: -0.1700
Data Index: 4554771 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4548. Min Range: -5.4548
Max Act: 4.7360. Min Act: -0.1700
Data Index: 3265023 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4548. Min Range: -5.4548
Max Act: 4.7360. Min Act: -0.1700
Data Index: 5023441 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4548. Min Range: -5.4548
Max Act: 4.7048. Min Act: -0.1700
Data Index: 2926016 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19