Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2801 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3686. Min Range: -7.3686
Max Act: 7.3686. Min Act: -0.1700
Data Index: 1536238 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3686. Min Range: -7.3686
Max Act: 7.3061. Min Act: -0.1700
Data Index: 854056 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3686. Min Range: -7.3686
Max Act: 7.1811. Min Act: -0.1700
Data Index: 5480824 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3686. Min Range: -7.3686
Max Act: 7.0249. Min Act: -0.1700
Data Index: 8575699 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3686. Min Range: -7.3686
Max Act: 6.9936. Min Act: -0.1700
Data Index: 1835385 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3686. Min Range: -7.3686
Max Act: 6.9311. Min Act: -0.1700
Data Index: 8740906 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3686. Min Range: -7.3686
Max Act: 6.8999. Min Act: -0.1700
Data Index: 1301931 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3686. Min Range: -7.3686
Max Act: 6.8999. Min Act: -0.1700
Data Index: 4800448 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3686. Min Range: -7.3686
Max Act: 6.8999. Min Act: -0.1700
Data Index: 3406802 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3686. Min Range: -7.3686
Max Act: 6.8999. Min Act: -0.1700
Data Index: 170701 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3686. Min Range: -7.3686
Max Act: 6.8686. Min Act: -0.1700
Data Index: 8383693 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3686. Min Range: -7.3686
Max Act: 6.8686. Min Act: -0.1700
Data Index: 3929759 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3686. Min Range: -7.3686
Max Act: 6.8061. Min Act: -0.1700
Data Index: 6866763 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3686. Min Range: -7.3686
Max Act: 6.8061. Min Act: -0.1700
Data Index: 5066666 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3686. Min Range: -7.3686
Max Act: 6.7749. Min Act: -0.1700
Data Index: 6866769 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3686. Min Range: -7.3686
Max Act: 6.7436. Min Act: -0.1700
Data Index: 8584040 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3686. Min Range: -7.3686
Max Act: 6.7124. Min Act: -0.1700
Data Index: 1005748 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3686. Min Range: -7.3686
Max Act: 6.7124. Min Act: -0.1700
Data Index: 5534896 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3686. Min Range: -7.3686
Max Act: 6.6811. Min Act: -0.1700
Data Index: 2316904 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3686. Min Range: -7.3686
Max Act: 6.7124. Min Act: -0.1700
Data Index: 7435666 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #19