Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3618 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2895. Min Range: -9.2895
Max Act: 9.2895. Min Act: -0.1700
Data Index: 132491 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2895. Min Range: -9.2895
Max Act: 8.8520. Min Act: -0.1700
Data Index: 5737610 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2895. Min Range: -9.2895
Max Act: 8.5395. Min Act: -0.1700
Data Index: 6575474 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2895. Min Range: -9.2895
Max Act: 8.6645. Min Act: -0.1700
Data Index: 4711451 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2895. Min Range: -9.2895
Max Act: 8.5395. Min Act: -0.1700
Data Index: 361520 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2895. Min Range: -9.2895
Max Act: 8.4145. Min Act: -0.1700
Data Index: 3138306 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2895. Min Range: -9.2895
Max Act: 8.4145. Min Act: -0.1700
Data Index: 531607 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2895. Min Range: -9.2895
Max Act: 8.3520. Min Act: -0.1700
Data Index: 779632 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2895. Min Range: -9.2895
Max Act: 8.3520. Min Act: -0.1700
Data Index: 5142136 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2895. Min Range: -9.2895
Max Act: 8.3520. Min Act: -0.1700
Data Index: 2599712 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2895. Min Range: -9.2895
Max Act: 8.2895. Min Act: -0.1700
Data Index: 3291854 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2895. Min Range: -9.2895
Max Act: 8.2270. Min Act: -0.1700
Data Index: 1626197 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2895. Min Range: -9.2895
Max Act: 8.2270. Min Act: -0.1700
Data Index: 6203987 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2895. Min Range: -9.2895
Max Act: 8.2270. Min Act: -0.1700
Data Index: 3349269 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2895. Min Range: -9.2895
Max Act: 8.1645. Min Act: -0.1700
Data Index: 3922671 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2895. Min Range: -9.2895
Max Act: 8.1020. Min Act: -0.1700
Data Index: 2579161 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2895. Min Range: -9.2895
Max Act: 8.1020. Min Act: -0.1700
Data Index: 6319546 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2895. Min Range: -9.2895
Max Act: 8.0395. Min Act: -0.1700
Data Index: 3336809 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2895. Min Range: -9.2895
Max Act: 8.0395. Min Act: -0.1700
Data Index: 6118407 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2895. Min Range: -9.2895
Max Act: 8.0395. Min Act: -0.1700
Data Index: 5735157 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #19