Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5069 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9193. Min Range: -4.9193
Max Act: 4.9193. Min Act: -0.1700
Data Index: 1182725 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9193. Min Range: -4.9193
Max Act: 4.7005. Min Act: -0.1700
Data Index: 35096 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9193. Min Range: -4.9193
Max Act: 4.5443. Min Act: -0.1700
Data Index: 7481042 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9193. Min Range: -4.9193
Max Act: 4.5443. Min Act: -0.1700
Data Index: 5641423 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9193. Min Range: -4.9193
Max Act: 4.3880. Min Act: -0.1700
Data Index: 2878677 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9193. Min Range: -4.9193
Max Act: 4.3255. Min Act: -0.1700
Data Index: 1025541 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9193. Min Range: -4.9193
Max Act: 4.2942. Min Act: -0.1700
Data Index: 2549598 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9193. Min Range: -4.9193
Max Act: 4.3255. Min Act: -0.1700
Data Index: 1874962 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9193. Min Range: -4.9193
Max Act: 4.2942. Min Act: -0.1700
Data Index: 861410 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9193. Min Range: -4.9193
Max Act: 4.2942. Min Act: -0.1700
Data Index: 6312370 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9193. Min Range: -4.9193
Max Act: 4.2630. Min Act: -0.1700
Data Index: 3662983 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9193. Min Range: -4.9193
Max Act: 4.2317. Min Act: -0.1700
Data Index: 7236080 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9193. Min Range: -4.9193
Max Act: 4.2005. Min Act: -0.1700
Data Index: 7439029 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9193. Min Range: -4.9193
Max Act: 4.2317. Min Act: -0.1700
Data Index: 4769369 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9193. Min Range: -4.9193
Max Act: 4.2005. Min Act: -0.1700
Data Index: 5260540 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9193. Min Range: -4.9193
Max Act: 4.1692. Min Act: -0.1700
Data Index: 3228478 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9193. Min Range: -4.9193
Max Act: 4.1692. Min Act: -0.1700
Data Index: 2749045 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9193. Min Range: -4.9193
Max Act: 4.1692. Min Act: -0.1700
Data Index: 283490 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9193. Min Range: -4.9193
Max Act: 4.1692. Min Act: -0.1700
Data Index: 5936954 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9193. Min Range: -4.9193
Max Act: 4.1692. Min Act: -0.1700
Data Index: 4935337 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #19