Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4905 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.2362. Min Range: -3.2362
Max Act: 3.2362. Min Act: -0.1700
Data Index: 3657597 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2362. Min Range: -3.2362
Max Act: 3.1891. Min Act: -0.1700
Data Index: 7320940 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2362. Min Range: -3.2362
Max Act: 3.1419. Min Act: -0.1700
Data Index: 511386 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2362. Min Range: -3.2362
Max Act: 3.1261. Min Act: -0.1700
Data Index: 4638125 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2362. Min Range: -3.2362
Max Act: 3.1261. Min Act: -0.1700
Data Index: 4401904 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2362. Min Range: -3.2362
Max Act: 3.0631. Min Act: -0.1700
Data Index: 8649476 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2362. Min Range: -3.2362
Max Act: 3.0788. Min Act: -0.1700
Data Index: 7080141 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2362. Min Range: -3.2362
Max Act: 3.0788. Min Act: -0.1700
Data Index: 5653600 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2362. Min Range: -3.2362
Max Act: 3.0631. Min Act: -0.1700
Data Index: 3726077 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2362. Min Range: -3.2362
Max Act: 3.0631. Min Act: -0.1700
Data Index: 3603215 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2362. Min Range: -3.2362
Max Act: 3.0315. Min Act: -0.1700
Data Index: 3235438 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2362. Min Range: -3.2362
Max Act: 3.0473. Min Act: -0.1700
Data Index: 4436954 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2362. Min Range: -3.2362
Max Act: 3.0315. Min Act: -0.1700
Data Index: 8270387 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2362. Min Range: -3.2362
Max Act: 3.0157. Min Act: -0.1700
Data Index: 6688162 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2362. Min Range: -3.2362
Max Act: 3.0157. Min Act: -0.1700
Data Index: 5185934 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2362. Min Range: -3.2362
Max Act: 2.9999. Min Act: -0.1700
Data Index: 348535 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2362. Min Range: -3.2362
Max Act: 2.9841. Min Act: -0.1700
Data Index: 4041274 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2362. Min Range: -3.2362
Max Act: 2.9841. Min Act: -0.1700
Data Index: 3727636 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2362. Min Range: -3.2362
Max Act: 2.9841. Min Act: -0.1700
Data Index: 6980774 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2362. Min Range: -3.2362
Max Act: 2.9683. Min Act: -0.1700
Data Index: 2621356 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #19