Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3909 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6160. Min Range: -3.6160
Max Act: 3.6160. Min Act: -0.1700
Data Index: 6455137 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6160. Min Range: -3.6160
Max Act: 3.6004. Min Act: -0.1700
Data Index: 1147355 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6160. Min Range: -3.6160
Max Act: 3.5377. Min Act: -0.1700
Data Index: 2928377 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6160. Min Range: -3.6160
Max Act: 3.5377. Min Act: -0.1700
Data Index: 4473593 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6160. Min Range: -3.6160
Max Act: 3.5064. Min Act: -0.1700
Data Index: 6520801 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6160. Min Range: -3.6160
Max Act: 3.4908. Min Act: -0.1700
Data Index: 6029304 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6160. Min Range: -3.6160
Max Act: 3.4438. Min Act: -0.1700
Data Index: 842188 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6160. Min Range: -3.6160
Max Act: 3.4281. Min Act: -0.1700
Data Index: 2679751 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6160. Min Range: -3.6160
Max Act: 3.4281. Min Act: -0.1700
Data Index: 2833134 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6160. Min Range: -3.6160
Max Act: 3.4124. Min Act: -0.1700
Data Index: 635937 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6160. Min Range: -3.6160
Max Act: 3.3967. Min Act: -0.1700
Data Index: 7077214 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6160. Min Range: -3.6160
Max Act: 3.3811. Min Act: -0.1700
Data Index: 1512031 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6160. Min Range: -3.6160
Max Act: 3.3811. Min Act: -0.1700
Data Index: 1720384 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6160. Min Range: -3.6160
Max Act: 3.3497. Min Act: -0.1700
Data Index: 1801651 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6160. Min Range: -3.6160
Max Act: 3.3340. Min Act: -0.1700
Data Index: 2546275 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6160. Min Range: -3.6160
Max Act: 3.3183. Min Act: -0.1700
Data Index: 7200757 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6160. Min Range: -3.6160
Max Act: 3.3340. Min Act: -0.1700
Data Index: 6355375 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6160. Min Range: -3.6160
Max Act: 3.3340. Min Act: -0.1700
Data Index: 5626484 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6160. Min Range: -3.6160
Max Act: 3.3183. Min Act: -0.1700
Data Index: 4479759 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6160. Min Range: -3.6160
Max Act: 3.3026. Min Act: -0.1700
Data Index: 4449445 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #19