Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3213 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2218. Min Range: -7.2218
Max Act: 7.2218. Min Act: -0.1700
Data Index: 4728429 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2218. Min Range: -7.2218
Max Act: 7.0030. Min Act: -0.1700
Data Index: 1102979 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2218. Min Range: -7.2218
Max Act: 6.9405. Min Act: -0.1700
Data Index: 1136712 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2218. Min Range: -7.2218
Max Act: 6.9405. Min Act: -0.1700
Data Index: 888329 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2218. Min Range: -7.2218
Max Act: 6.9405. Min Act: -0.1700
Data Index: 7766265 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2218. Min Range: -7.2218
Max Act: 6.9405. Min Act: -0.1700
Data Index: 6685452 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2218. Min Range: -7.2218
Max Act: 6.9718. Min Act: -0.1700
Data Index: 399445 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2218. Min Range: -7.2218
Max Act: 6.9093. Min Act: -0.1700
Data Index: 6873746 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2218. Min Range: -7.2218
Max Act: 6.8468. Min Act: -0.1700
Data Index: 5520161 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2218. Min Range: -7.2218
Max Act: 6.8468. Min Act: -0.1700
Data Index: 6206571 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2218. Min Range: -7.2218
Max Act: 6.8468. Min Act: -0.1700
Data Index: 4880830 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2218. Min Range: -7.2218
Max Act: 6.8468. Min Act: -0.1700
Data Index: 4109015 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2218. Min Range: -7.2218
Max Act: 6.8468. Min Act: -0.1700
Data Index: 4407037 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2218. Min Range: -7.2218
Max Act: 6.8155. Min Act: -0.1700
Data Index: 3583131 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2218. Min Range: -7.2218
Max Act: 6.8155. Min Act: -0.1700
Data Index: 4192092 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2218. Min Range: -7.2218
Max Act: 6.8155. Min Act: -0.1700
Data Index: 5554809 (Open Web Text)
Max Activating Token Index: 549
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2218. Min Range: -7.2218
Max Act: 6.6905. Min Act: -0.1700
Data Index: 3175547 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2218. Min Range: -7.2218
Max Act: 6.7218. Min Act: -0.1700
Data Index: 3687090 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2218. Min Range: -7.2218
Max Act: 6.6593. Min Act: -0.1700
Data Index: 6114774 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2218. Min Range: -7.2218
Max Act: 6.6593. Min Act: -0.1700
Data Index: 3972810 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #19