Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3002 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0687. Min Range: -5.0687
Max Act: 5.0687. Min Act: -0.1700
Data Index: 5623021 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0687. Min Range: -5.0687
Max Act: 5.0687. Min Act: -0.1700
Data Index: 3105340 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0687. Min Range: -5.0687
Max Act: 5.0687. Min Act: -0.1700
Data Index: 6318473 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0687. Min Range: -5.0687
Max Act: 5.0062. Min Act: -0.1700
Data Index: 3780096 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0687. Min Range: -5.0687
Max Act: 5.0062. Min Act: -0.1700
Data Index: 1297835 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0687. Min Range: -5.0687
Max Act: 4.9749. Min Act: -0.1700
Data Index: 4101634 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0687. Min Range: -5.0687
Max Act: 4.9749. Min Act: -0.1700
Data Index: 850760 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0687. Min Range: -5.0687
Max Act: 4.9749. Min Act: -0.1700
Data Index: 3603320 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0687. Min Range: -5.0687
Max Act: 4.9749. Min Act: -0.1700
Data Index: 175975 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0687. Min Range: -5.0687
Max Act: 4.9749. Min Act: -0.1700
Data Index: 5476024 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0687. Min Range: -5.0687
Max Act: 4.9437. Min Act: -0.1700
Data Index: 4004330 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0687. Min Range: -5.0687
Max Act: 4.9124. Min Act: -0.1700
Data Index: 839466 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0687. Min Range: -5.0687
Max Act: 4.9437. Min Act: -0.1700
Data Index: 8409248 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0687. Min Range: -5.0687
Max Act: 4.9124. Min Act: -0.1700
Data Index: 2370449 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0687. Min Range: -5.0687
Max Act: 4.9437. Min Act: -0.1700
Data Index: 1395436 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0687. Min Range: -5.0687
Max Act: 4.9437. Min Act: -0.1700
Data Index: 6055269 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0687. Min Range: -5.0687
Max Act: 4.9437. Min Act: -0.1700
Data Index: 7323371 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0687. Min Range: -5.0687
Max Act: 4.9124. Min Act: -0.1700
Data Index: 6264636 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0687. Min Range: -5.0687
Max Act: 4.9124. Min Act: -0.1700
Data Index: 2238983 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0687. Min Range: -5.0687
Max Act: 4.9124. Min Act: -0.1700
Data Index: 3174021 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #19