Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3282 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2052. Min Range: -7.2052
Max Act: 7.2052. Min Act: -0.1700
Data Index: 6745396 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2052. Min Range: -7.2052
Max Act: 7.1115. Min Act: -0.1700
Data Index: 17546 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2052. Min Range: -7.2052
Max Act: 6.9865. Min Act: -0.1700
Data Index: 1295764 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2052. Min Range: -7.2052
Max Act: 6.9552. Min Act: -0.1700
Data Index: 4281680 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2052. Min Range: -7.2052
Max Act: 6.9552. Min Act: -0.1700
Data Index: 4174976 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2052. Min Range: -7.2052
Max Act: 6.8927. Min Act: -0.1700
Data Index: 5035203 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2052. Min Range: -7.2052
Max Act: 6.9240. Min Act: -0.1700
Data Index: 3169946 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2052. Min Range: -7.2052
Max Act: 6.8927. Min Act: -0.1700
Data Index: 8755594 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2052. Min Range: -7.2052
Max Act: 6.8927. Min Act: -0.1700
Data Index: 1360701 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2052. Min Range: -7.2052
Max Act: 6.8302. Min Act: -0.1700
Data Index: 4067244 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2052. Min Range: -7.2052
Max Act: 6.8302. Min Act: -0.1700
Data Index: 570717 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2052. Min Range: -7.2052
Max Act: 6.7677. Min Act: -0.1700
Data Index: 368225 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2052. Min Range: -7.2052
Max Act: 6.7677. Min Act: -0.1700
Data Index: 8257826 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2052. Min Range: -7.2052
Max Act: 6.7677. Min Act: -0.1700
Data Index: 5046 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2052. Min Range: -7.2052
Max Act: 6.7677. Min Act: -0.1700
Data Index: 8609973 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2052. Min Range: -7.2052
Max Act: 6.7365. Min Act: -0.1700
Data Index: 6005643 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2052. Min Range: -7.2052
Max Act: 6.7365. Min Act: -0.1700
Data Index: 5396904 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2052. Min Range: -7.2052
Max Act: 6.7365. Min Act: -0.1700
Data Index: 7791762 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2052. Min Range: -7.2052
Max Act: 6.7365. Min Act: -0.1700
Data Index: 4281683 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2052. Min Range: -7.2052
Max Act: 6.7052. Min Act: -0.1700
Data Index: 2072894 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19