Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6192 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2029. Min Range: -7.2029
Max Act: 7.2029. Min Act: -0.1700
Data Index: 626912 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2029. Min Range: -7.2029
Max Act: 7.1404. Min Act: -0.1700
Data Index: 3235791 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2029. Min Range: -7.2029
Max Act: 7.0467. Min Act: -0.1700
Data Index: 6179329 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2029. Min Range: -7.2029
Max Act: 6.7967. Min Act: -0.1700
Data Index: 3653186 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2029. Min Range: -7.2029
Max Act: 6.7342. Min Act: -0.1700
Data Index: 5160838 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2029. Min Range: -7.2029
Max Act: 6.6717. Min Act: -0.1700
Data Index: 6641012 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2029. Min Range: -7.2029
Max Act: 6.6717. Min Act: -0.1700
Data Index: 1942777 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2029. Min Range: -7.2029
Max Act: 6.5779. Min Act: -0.1700
Data Index: 4411035 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2029. Min Range: -7.2029
Max Act: 6.5154. Min Act: -0.1700
Data Index: 5564645 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2029. Min Range: -7.2029
Max Act: 6.4842. Min Act: -0.1700
Data Index: 6716240 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2029. Min Range: -7.2029
Max Act: 6.4529. Min Act: -0.1700
Data Index: 3467409 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2029. Min Range: -7.2029
Max Act: 6.4529. Min Act: -0.1700
Data Index: 3655103 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2029. Min Range: -7.2029
Max Act: 6.3904. Min Act: -0.1700
Data Index: 4754714 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2029. Min Range: -7.2029
Max Act: 6.3904. Min Act: -0.1700
Data Index: 8579237 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2029. Min Range: -7.2029
Max Act: 6.3279. Min Act: -0.1700
Data Index: 4516588 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2029. Min Range: -7.2029
Max Act: 6.2967. Min Act: -0.1700
Data Index: 6796138 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2029. Min Range: -7.2029
Max Act: 6.2967. Min Act: -0.1700
Data Index: 5850656 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2029. Min Range: -7.2029
Max Act: 6.2967. Min Act: -0.1700
Data Index: 2636811 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2029. Min Range: -7.2029
Max Act: 6.2967. Min Act: -0.1700
Data Index: 4219038 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2029. Min Range: -7.2029
Max Act: 6.2654. Min Act: -0.1700
Data Index: 2411198 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #19