Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3249 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.3958. Min Range: -7.3958
Max Act: 7.3958. Min Act: -0.1700
Data Index: 1001192 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3958. Min Range: -7.3958
Max Act: 7.3333. Min Act: -0.1700
Data Index: 7401383 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3958. Min Range: -7.3958
Max Act: 7.3333. Min Act: -0.1700
Data Index: 434060 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3958. Min Range: -7.3958
Max Act: 7.1458. Min Act: -0.1700
Data Index: 8176781 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3958. Min Range: -7.3958
Max Act: 7.1145. Min Act: -0.1700
Data Index: 3886723 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3958. Min Range: -7.3958
Max Act: 7.0520. Min Act: -0.1700
Data Index: 7507080 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3958. Min Range: -7.3958
Max Act: 6.9895. Min Act: -0.1700
Data Index: 3165465 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3958. Min Range: -7.3958
Max Act: 6.8645. Min Act: -0.1700
Data Index: 4887854 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3958. Min Range: -7.3958
Max Act: 6.8645. Min Act: -0.1700
Data Index: 4346520 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3958. Min Range: -7.3958
Max Act: 6.8333. Min Act: -0.1700
Data Index: 5130283 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3958. Min Range: -7.3958
Max Act: 6.8333. Min Act: -0.1700
Data Index: 5049055 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3958. Min Range: -7.3958
Max Act: 6.8020. Min Act: -0.1700
Data Index: 368835 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3958. Min Range: -7.3958
Max Act: 6.8020. Min Act: -0.1700
Data Index: 3929029 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3958. Min Range: -7.3958
Max Act: 6.7708. Min Act: -0.1700
Data Index: 1031536 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3958. Min Range: -7.3958
Max Act: 6.8333. Min Act: -0.1700
Data Index: 8003968 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3958. Min Range: -7.3958
Max Act: 6.8020. Min Act: -0.1700
Data Index: 271943 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3958. Min Range: -7.3958
Max Act: 6.7708. Min Act: -0.1700
Data Index: 1005384 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3958. Min Range: -7.3958
Max Act: 6.8020. Min Act: -0.1700
Data Index: 2168294 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3958. Min Range: -7.3958
Max Act: 6.7708. Min Act: -0.1700
Data Index: 5421537 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3958. Min Range: -7.3958
Max Act: 6.7708. Min Act: -0.1700
Data Index: 5567313 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #19