Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3008 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8931. Min Range: -4.8931
Max Act: 4.8931. Min Act: -0.1700
Data Index: 7927507 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8931. Min Range: -4.8931
Max Act: 4.7681. Min Act: -0.1700
Data Index: 2441022 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8931. Min Range: -4.8931
Max Act: 4.7681. Min Act: -0.1700
Data Index: 4842161 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8931. Min Range: -4.8931
Max Act: 4.7681. Min Act: -0.1700
Data Index: 6545965 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8931. Min Range: -4.8931
Max Act: 4.7055. Min Act: -0.1700
Data Index: 4055134 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8931. Min Range: -4.8931
Max Act: 4.7055. Min Act: -0.1700
Data Index: 2300813 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8931. Min Range: -4.8931
Max Act: 4.7368. Min Act: -0.1700
Data Index: 8473873 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8931. Min Range: -4.8931
Max Act: 4.7055. Min Act: -0.1700
Data Index: 2206149 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8931. Min Range: -4.8931
Max Act: 4.7055. Min Act: -0.1700
Data Index: 8212144 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8931. Min Range: -4.8931
Max Act: 4.7055. Min Act: -0.1700
Data Index: 6730928 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8931. Min Range: -4.8931
Max Act: 4.6743. Min Act: -0.1700
Data Index: 495195 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8931. Min Range: -4.8931
Max Act: 4.6743. Min Act: -0.1700
Data Index: 6505540 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8931. Min Range: -4.8931
Max Act: 4.6743. Min Act: -0.1700
Data Index: 6469535 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8931. Min Range: -4.8931
Max Act: 4.6743. Min Act: -0.1700
Data Index: 3423941 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8931. Min Range: -4.8931
Max Act: 4.6430. Min Act: -0.1700
Data Index: 1030867 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8931. Min Range: -4.8931
Max Act: 4.6743. Min Act: -0.1700
Data Index: 5471885 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8931. Min Range: -4.8931
Max Act: 4.6118. Min Act: -0.1700
Data Index: 6380265 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8931. Min Range: -4.8931
Max Act: 4.6118. Min Act: -0.1700
Data Index: 6359465 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8931. Min Range: -4.8931
Max Act: 4.5805. Min Act: -0.1700
Data Index: 5106772 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8931. Min Range: -4.8931
Max Act: 4.5493. Min Act: -0.1700
Data Index: 7664617 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #19