Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3166 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.6082. Min Range: -3.6082
Max Act: 3.6082. Min Act: -0.1700
Data Index: 6921460 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.6082. Min Range: -3.6082
Max Act: 3.6082. Min Act: -0.1700
Data Index: 7239426 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.6082. Min Range: -3.6082
Max Act: 3.6082. Min Act: -0.1700
Data Index: 2366412 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.6082. Min Range: -3.6082
Max Act: 3.5456. Min Act: -0.1700
Data Index: 23719 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.6082. Min Range: -3.6082
Max Act: 3.5143. Min Act: -0.1700
Data Index: 6532550 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.6082. Min Range: -3.6082
Max Act: 3.5143. Min Act: -0.1700
Data Index: 4342618 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.6082. Min Range: -3.6082
Max Act: 3.5143. Min Act: -0.1700
Data Index: 7928528 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.6082. Min Range: -3.6082
Max Act: 3.5143. Min Act: -0.1700
Data Index: 1568794 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.6082. Min Range: -3.6082
Max Act: 3.5143. Min Act: -0.1700
Data Index: 6100451 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.6082. Min Range: -3.6082
Max Act: 3.5143. Min Act: -0.1700
Data Index: 5799071 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.6082. Min Range: -3.6082
Max Act: 3.5143. Min Act: -0.1700
Data Index: 2926057 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.6082. Min Range: -3.6082
Max Act: 3.4830. Min Act: -0.1700
Data Index: 3071179 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.6082. Min Range: -3.6082
Max Act: 3.4830. Min Act: -0.1700
Data Index: 901297 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.6082. Min Range: -3.6082
Max Act: 3.4516. Min Act: -0.1700
Data Index: 7264016 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.6082. Min Range: -3.6082
Max Act: 3.4830. Min Act: -0.1700
Data Index: 6702159 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.6082. Min Range: -3.6082
Max Act: 3.4830. Min Act: -0.1700
Data Index: 3759621 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.6082. Min Range: -3.6082
Max Act: 3.4830. Min Act: -0.1700
Data Index: 6166734 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.6082. Min Range: -3.6082
Max Act: 3.4830. Min Act: -0.1700
Data Index: 5620671 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.6082. Min Range: -3.6082
Max Act: 3.4830. Min Act: -0.1700
Data Index: 8184191 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.6082. Min Range: -3.6082
Max Act: 3.4830. Min Act: -0.1700
Data Index: 3146078 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #19