Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3158 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8148. Min Range: -7.8148
Max Act: 7.8148. Min Act: -0.1700
Data Index: 6983849 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8148. Min Range: -7.8148
Max Act: 7.8148. Min Act: -0.1700
Data Index: 6990217 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8148. Min Range: -7.8148
Max Act: 7.8148. Min Act: -0.1700
Data Index: 2171795 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8148. Min Range: -7.8148
Max Act: 7.7523. Min Act: -0.1700
Data Index: 2759870 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8148. Min Range: -7.8148
Max Act: 7.5648. Min Act: -0.1700
Data Index: 6983851 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8148. Min Range: -7.8148
Max Act: 7.5336. Min Act: -0.1700
Data Index: 6773202 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8148. Min Range: -7.8148
Max Act: 7.5023. Min Act: -0.1700
Data Index: 2743484 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8148. Min Range: -7.8148
Max Act: 7.5023. Min Act: -0.1700
Data Index: 2479981 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8148. Min Range: -7.8148
Max Act: 7.5023. Min Act: -0.1700
Data Index: 6178128 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8148. Min Range: -7.8148
Max Act: 7.4398. Min Act: -0.1700
Data Index: 6983850 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8148. Min Range: -7.8148
Max Act: 7.4086. Min Act: -0.1700
Data Index: 203946 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8148. Min Range: -7.8148
Max Act: 7.4086. Min Act: -0.1700
Data Index: 8129600 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8148. Min Range: -7.8148
Max Act: 7.4086. Min Act: -0.1700
Data Index: 8152981 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8148. Min Range: -7.8148
Max Act: 7.3461. Min Act: -0.1700
Data Index: 2456914 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8148. Min Range: -7.8148
Max Act: 7.3773. Min Act: -0.1700
Data Index: 6773190 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8148. Min Range: -7.8148
Max Act: 7.3773. Min Act: -0.1700
Data Index: 5434935 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8148. Min Range: -7.8148
Max Act: 7.3773. Min Act: -0.1700
Data Index: 2183494 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8148. Min Range: -7.8148
Max Act: 7.3461. Min Act: -0.1700
Data Index: 6631457 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8148. Min Range: -7.8148
Max Act: 7.3148. Min Act: -0.1700
Data Index: 3851507 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8148. Min Range: -7.8148
Max Act: 7.3148. Min Act: -0.1700
Data Index: 5347485 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #19