Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3332 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8043. Min Range: -5.8043
Max Act: 5.8043. Min Act: -0.1700
Data Index: 4385886 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8043. Min Range: -5.8043
Max Act: 5.4605. Min Act: -0.1700
Data Index: 6672270 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8043. Min Range: -5.8043
Max Act: 5.4918. Min Act: -0.1700
Data Index: 5311575 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8043. Min Range: -5.8043
Max Act: 5.4605. Min Act: -0.1700
Data Index: 7451035 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8043. Min Range: -5.8043
Max Act: 5.3668. Min Act: -0.1700
Data Index: 2174075 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8043. Min Range: -5.8043
Max Act: 5.3355. Min Act: -0.1700
Data Index: 6004980 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8043. Min Range: -5.8043
Max Act: 5.3043. Min Act: -0.1700
Data Index: 2424638 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8043. Min Range: -5.8043
Max Act: 5.3043. Min Act: -0.1700
Data Index: 1199324 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8043. Min Range: -5.8043
Max Act: 5.3043. Min Act: -0.1700
Data Index: 7388465 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8043. Min Range: -5.8043
Max Act: 5.2418. Min Act: -0.1700
Data Index: 1783685 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8043. Min Range: -5.8043
Max Act: 5.2418. Min Act: -0.1700
Data Index: 2424637 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8043. Min Range: -5.8043
Max Act: 5.2105. Min Act: -0.1700
Data Index: 8216514 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8043. Min Range: -5.8043
Max Act: 5.2105. Min Act: -0.1700
Data Index: 5795522 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8043. Min Range: -5.8043
Max Act: 5.2105. Min Act: -0.1700
Data Index: 30850 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8043. Min Range: -5.8043
Max Act: 5.1793. Min Act: -0.1700
Data Index: 8802066 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8043. Min Range: -5.8043
Max Act: 5.1480. Min Act: -0.1700
Data Index: 6262477 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8043. Min Range: -5.8043
Max Act: 5.1168. Min Act: -0.1700
Data Index: 2505062 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8043. Min Range: -5.8043
Max Act: 5.1480. Min Act: -0.1700
Data Index: 7643600 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8043. Min Range: -5.8043
Max Act: 5.1480. Min Act: -0.1700
Data Index: 8216529 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8043. Min Range: -5.8043
Max Act: 5.1168. Min Act: -0.1700
Data Index: 5584059 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #19