Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4330 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7463. Min Range: -5.7463
Max Act: 5.7463. Min Act: -0.1700
Data Index: 2479685 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7463. Min Range: -5.7463
Max Act: 5.7150. Min Act: -0.1700
Data Index: 4395058 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7463. Min Range: -5.7463
Max Act: 5.6838. Min Act: -0.1700
Data Index: 2370283 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7463. Min Range: -5.7463
Max Act: 5.6525. Min Act: -0.1700
Data Index: 5330791 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7463. Min Range: -5.7463
Max Act: 5.6525. Min Act: -0.1700
Data Index: 8519513 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7463. Min Range: -5.7463
Max Act: 5.6213. Min Act: -0.1700
Data Index: 3352416 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7463. Min Range: -5.7463
Max Act: 5.6213. Min Act: -0.1700
Data Index: 3833552 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7463. Min Range: -5.7463
Max Act: 5.6213. Min Act: -0.1700
Data Index: 2370297 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7463. Min Range: -5.7463
Max Act: 5.6213. Min Act: -0.1700
Data Index: 6219029 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7463. Min Range: -5.7463
Max Act: 5.5588. Min Act: -0.1700
Data Index: 6033278 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7463. Min Range: -5.7463
Max Act: 5.5900. Min Act: -0.1700
Data Index: 1364714 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7463. Min Range: -5.7463
Max Act: 5.5588. Min Act: -0.1700
Data Index: 8787134 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7463. Min Range: -5.7463
Max Act: 5.5588. Min Act: -0.1700
Data Index: 3250 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7463. Min Range: -5.7463
Max Act: 5.5588. Min Act: -0.1700
Data Index: 4270819 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7463. Min Range: -5.7463
Max Act: 5.5588. Min Act: -0.1700
Data Index: 7632298 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7463. Min Range: -5.7463
Max Act: 5.5588. Min Act: -0.1700
Data Index: 8743485 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7463. Min Range: -5.7463
Max Act: 5.5588. Min Act: -0.1700
Data Index: 1418032 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7463. Min Range: -5.7463
Max Act: 5.5275. Min Act: -0.1700
Data Index: 7905125 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7463. Min Range: -5.7463
Max Act: 5.4963. Min Act: -0.1700
Data Index: 6228799 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7463. Min Range: -5.7463
Max Act: 5.4963. Min Act: -0.1700
Data Index: 4658789 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #19