Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3803 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6232. Min Range: -6.6232
Max Act: 6.6232. Min Act: -0.1700
Data Index: 7841040 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6232. Min Range: -6.6232
Max Act: 6.5919. Min Act: -0.1700
Data Index: 488185 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6232. Min Range: -6.6232
Max Act: 6.3419. Min Act: -0.1700
Data Index: 121526 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6232. Min Range: -6.6232
Max Act: 6.3107. Min Act: -0.1700
Data Index: 7103897 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6232. Min Range: -6.6232
Max Act: 6.2794. Min Act: -0.1700
Data Index: 7196153 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6232. Min Range: -6.6232
Max Act: 6.2169. Min Act: -0.1700
Data Index: 2862381 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6232. Min Range: -6.6232
Max Act: 6.1857. Min Act: -0.1700
Data Index: 7002739 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6232. Min Range: -6.6232
Max Act: 6.1857. Min Act: -0.1700
Data Index: 5883755 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6232. Min Range: -6.6232
Max Act: 6.1857. Min Act: -0.1700
Data Index: 935666 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6232. Min Range: -6.6232
Max Act: 6.1544. Min Act: -0.1700
Data Index: 8613690 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6232. Min Range: -6.6232
Max Act: 6.1232. Min Act: -0.1700
Data Index: 2576187 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6232. Min Range: -6.6232
Max Act: 6.1544. Min Act: -0.1700
Data Index: 6713987 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6232. Min Range: -6.6232
Max Act: 6.0919. Min Act: -0.1700
Data Index: 4040819 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6232. Min Range: -6.6232
Max Act: 6.0919. Min Act: -0.1700
Data Index: 6317293 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6232. Min Range: -6.6232
Max Act: 6.0919. Min Act: -0.1700
Data Index: 2089919 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6232. Min Range: -6.6232
Max Act: 6.0919. Min Act: -0.1700
Data Index: 627908 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6232. Min Range: -6.6232
Max Act: 6.0607. Min Act: -0.1700
Data Index: 5821121 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6232. Min Range: -6.6232
Max Act: 6.0607. Min Act: -0.1700
Data Index: 6331204 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6232. Min Range: -6.6232
Max Act: 6.0607. Min Act: -0.1700
Data Index: 1161694 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6232. Min Range: -6.6232
Max Act: 6.0607. Min Act: -0.1700
Data Index: 5571121 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #19