Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2228 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3101. Min Range: -6.3101
Max Act: 6.3101. Min Act: -0.1700
Data Index: 8705176 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3101. Min Range: -6.3101
Max Act: 6.2476. Min Act: -0.1700
Data Index: 14839 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3101. Min Range: -6.3101
Max Act: 6.0601. Min Act: -0.1700
Data Index: 8404375 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3101. Min Range: -6.3101
Max Act: 6.0601. Min Act: -0.1700
Data Index: 7661452 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3101. Min Range: -6.3101
Max Act: 5.9663. Min Act: -0.1700
Data Index: 3840962 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3101. Min Range: -6.3101
Max Act: 5.9351. Min Act: -0.1700
Data Index: 1354151 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3101. Min Range: -6.3101
Max Act: 5.8413. Min Act: -0.1700
Data Index: 8450668 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3101. Min Range: -6.3101
Max Act: 5.8726. Min Act: -0.1700
Data Index: 1856544 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3101. Min Range: -6.3101
Max Act: 5.8726. Min Act: -0.1700
Data Index: 7452714 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3101. Min Range: -6.3101
Max Act: 5.8413. Min Act: -0.1700
Data Index: 1504255 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3101. Min Range: -6.3101
Max Act: 5.7788. Min Act: -0.1700
Data Index: 2570732 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3101. Min Range: -6.3101
Max Act: 5.7788. Min Act: -0.1700
Data Index: 3339271 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3101. Min Range: -6.3101
Max Act: 5.7163. Min Act: -0.1700
Data Index: 2666917 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3101. Min Range: -6.3101
Max Act: 5.6538. Min Act: -0.1700
Data Index: 4063645 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3101. Min Range: -6.3101
Max Act: 5.6538. Min Act: -0.1700
Data Index: 7718075 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3101. Min Range: -6.3101
Max Act: 5.6538. Min Act: -0.1700
Data Index: 3304421 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3101. Min Range: -6.3101
Max Act: 5.6538. Min Act: -0.1700
Data Index: 6477860 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3101. Min Range: -6.3101
Max Act: 5.6538. Min Act: -0.1700
Data Index: 2382183 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3101. Min Range: -6.3101
Max Act: 5.6226. Min Act: -0.1700
Data Index: 2415400 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3101. Min Range: -6.3101
Max Act: 5.6538. Min Act: -0.1700
Data Index: 4357333 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #19