Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2642 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3148. Min Range: -6.3148
Max Act: 6.3148. Min Act: -0.1700
Data Index: 1919062 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3148. Min Range: -6.3148
Max Act: 6.0961. Min Act: -0.1700
Data Index: 5440061 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3148. Min Range: -6.3148
Max Act: 6.0961. Min Act: -0.1700
Data Index: 5212538 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3148. Min Range: -6.3148
Max Act: 6.0336. Min Act: -0.1700
Data Index: 5986447 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3148. Min Range: -6.3148
Max Act: 6.0023. Min Act: -0.1700
Data Index: 1541206 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3148. Min Range: -6.3148
Max Act: 6.0023. Min Act: -0.1700
Data Index: 5724917 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3148. Min Range: -6.3148
Max Act: 5.9711. Min Act: -0.1700
Data Index: 3166830 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3148. Min Range: -6.3148
Max Act: 5.9711. Min Act: -0.1700
Data Index: 5245879 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3148. Min Range: -6.3148
Max Act: 5.9398. Min Act: -0.1700
Data Index: 5517913 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3148. Min Range: -6.3148
Max Act: 5.9398. Min Act: -0.1700
Data Index: 5121735 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3148. Min Range: -6.3148
Max Act: 5.9398. Min Act: -0.1700
Data Index: 5884385 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3148. Min Range: -6.3148
Max Act: 5.9398. Min Act: -0.1700
Data Index: 5865208 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3148. Min Range: -6.3148
Max Act: 5.9398. Min Act: -0.1700
Data Index: 5363622 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3148. Min Range: -6.3148
Max Act: 5.9086. Min Act: -0.1700
Data Index: 1465560 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3148. Min Range: -6.3148
Max Act: 5.9086. Min Act: -0.1700
Data Index: 8486674 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3148. Min Range: -6.3148
Max Act: 5.9086. Min Act: -0.1700
Data Index: 5212537 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3148. Min Range: -6.3148
Max Act: 5.9086. Min Act: -0.1700
Data Index: 2033106 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3148. Min Range: -6.3148
Max Act: 5.9398. Min Act: -0.1700
Data Index: 1173607 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3148. Min Range: -6.3148
Max Act: 5.8773. Min Act: -0.1700
Data Index: 616958 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3148. Min Range: -6.3148
Max Act: 5.8461. Min Act: -0.1700
Data Index: 659100 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #19