Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3204 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.8904. Min Range: -4.8904
Max Act: 4.8904. Min Act: -0.1700
Data Index: 5136575 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8904. Min Range: -4.8904
Max Act: 4.8591. Min Act: -0.1700
Data Index: 379836 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8904. Min Range: -4.8904
Max Act: 4.8591. Min Act: -0.1698
Data Index: 3754561 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8904. Min Range: -4.8904
Max Act: 4.8279. Min Act: -0.1700
Data Index: 8092773 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8904. Min Range: -4.8904
Max Act: 4.8279. Min Act: -0.1700
Data Index: 3318308 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8904. Min Range: -4.8904
Max Act: 4.7966. Min Act: -0.1700
Data Index: 1463952 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8904. Min Range: -4.8904
Max Act: 4.7966. Min Act: -0.1700
Data Index: 2707791 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8904. Min Range: -4.8904
Max Act: 4.7966. Min Act: -0.1700
Data Index: 1325917 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8904. Min Range: -4.8904
Max Act: 4.7966. Min Act: -0.1700
Data Index: 8693762 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8904. Min Range: -4.8904
Max Act: 4.7966. Min Act: -0.1700
Data Index: 138298 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8904. Min Range: -4.8904
Max Act: 4.7966. Min Act: -0.1700
Data Index: 7613547 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8904. Min Range: -4.8904
Max Act: 4.7966. Min Act: -0.1700
Data Index: 1737100 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8904. Min Range: -4.8904
Max Act: 4.7966. Min Act: -0.1700
Data Index: 5075796 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8904. Min Range: -4.8904
Max Act: 4.7966. Min Act: -0.1700
Data Index: 1286501 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8904. Min Range: -4.8904
Max Act: 4.7654. Min Act: -0.1700
Data Index: 7100419 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8904. Min Range: -4.8904
Max Act: 4.7654. Min Act: -0.1700
Data Index: 138297 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8904. Min Range: -4.8904
Max Act: 4.7654. Min Act: -0.1700
Data Index: 2667315 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8904. Min Range: -4.8904
Max Act: 4.7654. Min Act: -0.1700
Data Index: 7181246 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8904. Min Range: -4.8904
Max Act: 4.7654. Min Act: -0.1700
Data Index: 4596928 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8904. Min Range: -4.8904
Max Act: 4.7654. Min Act: -0.1700
Data Index: 1151964 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #19