Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4792 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.4870. Min Range: -5.4870
Max Act: 5.4870. Min Act: -0.1700
Data Index: 3417256 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4870. Min Range: -5.4870
Max Act: 5.3308. Min Act: -0.1700
Data Index: 2085132 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4870. Min Range: -5.4870
Max Act: 5.3308. Min Act: -0.1700
Data Index: 1393211 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4870. Min Range: -5.4870
Max Act: 5.2995. Min Act: -0.1700
Data Index: 2360464 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4870. Min Range: -5.4870
Max Act: 5.2995. Min Act: -0.1700
Data Index: 4796393 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4870. Min Range: -5.4870
Max Act: 5.2058. Min Act: -0.1700
Data Index: 268880 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4870. Min Range: -5.4870
Max Act: 5.2370. Min Act: -0.1700
Data Index: 1318401 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4870. Min Range: -5.4870
Max Act: 5.2370. Min Act: -0.1700
Data Index: 3837381 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4870. Min Range: -5.4870
Max Act: 5.1745. Min Act: -0.1700
Data Index: 7099878 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4870. Min Range: -5.4870
Max Act: 5.1745. Min Act: -0.1700
Data Index: 5075100 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4870. Min Range: -5.4870
Max Act: 5.1433. Min Act: -0.1700
Data Index: 820531 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4870. Min Range: -5.4870
Max Act: 5.1433. Min Act: -0.1700
Data Index: 2282748 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4870. Min Range: -5.4870
Max Act: 5.1120. Min Act: -0.1700
Data Index: 3437028 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4870. Min Range: -5.4870
Max Act: 5.0808. Min Act: -0.1700
Data Index: 7655919 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4870. Min Range: -5.4870
Max Act: 5.0808. Min Act: -0.1700
Data Index: 6578858 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4870. Min Range: -5.4870
Max Act: 5.1120. Min Act: -0.1700
Data Index: 4979926 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4870. Min Range: -5.4870
Max Act: 5.0808. Min Act: -0.1700
Data Index: 5672635 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4870. Min Range: -5.4870
Max Act: 5.0808. Min Act: -0.1700
Data Index: 763973 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4870. Min Range: -5.4870
Max Act: 5.0808. Min Act: -0.1700
Data Index: 5138474 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4870. Min Range: -5.4870
Max Act: 5.0495. Min Act: -0.1700
Data Index: 4874882 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #19