Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2505 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4887. Min Range: -7.4887
Max Act: 7.4887. Min Act: -0.1700
Data Index: 7433924 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4887. Min Range: -7.4887
Max Act: 7.3637. Min Act: -0.1700
Data Index: 4068027 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4887. Min Range: -7.4887
Max Act: 7.3012. Min Act: -0.1700
Data Index: 909187 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4887. Min Range: -7.4887
Max Act: 7.2700. Min Act: -0.1700
Data Index: 6418320 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4887. Min Range: -7.4887
Max Act: 7.1450. Min Act: -0.1700
Data Index: 1408842 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4887. Min Range: -7.4887
Max Act: 7.1450. Min Act: -0.1700
Data Index: 561312 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4887. Min Range: -7.4887
Max Act: 7.1450. Min Act: -0.1700
Data Index: 296265 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4887. Min Range: -7.4887
Max Act: 7.1137. Min Act: -0.1700
Data Index: 4870161 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4887. Min Range: -7.4887
Max Act: 7.0200. Min Act: -0.1700
Data Index: 5105172 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4887. Min Range: -7.4887
Max Act: 6.9575. Min Act: -0.1700
Data Index: 2461183 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4887. Min Range: -7.4887
Max Act: 6.9575. Min Act: -0.1700
Data Index: 34304 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4887. Min Range: -7.4887
Max Act: 6.9575. Min Act: -0.1700
Data Index: 678697 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4887. Min Range: -7.4887
Max Act: 6.9575. Min Act: -0.1700
Data Index: 2526566 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4887. Min Range: -7.4887
Max Act: 6.9575. Min Act: -0.1700
Data Index: 4347115 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4887. Min Range: -7.4887
Max Act: 6.9575. Min Act: -0.1700
Data Index: 5207986 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4887. Min Range: -7.4887
Max Act: 6.9262. Min Act: -0.1700
Data Index: 4811545 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4887. Min Range: -7.4887
Max Act: 6.8950. Min Act: -0.1700
Data Index: 6269322 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4887. Min Range: -7.4887
Max Act: 6.9262. Min Act: -0.1700
Data Index: 7163310 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4887. Min Range: -7.4887
Max Act: 6.8950. Min Act: -0.1700
Data Index: 2536241 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4887. Min Range: -7.4887
Max Act: 6.8637. Min Act: -0.1700
Data Index: 2518885 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #19