Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6040 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6709. Min Range: -7.6709
Max Act: 7.6709. Min Act: -0.1700
Data Index: 6762363 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6709. Min Range: -7.6709
Max Act: 7.5772. Min Act: -0.1700
Data Index: 2777096 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6709. Min Range: -7.6709
Max Act: 7.4209. Min Act: -0.1700
Data Index: 6825557 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6709. Min Range: -7.6709
Max Act: 7.3897. Min Act: -0.1700
Data Index: 4883773 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6709. Min Range: -7.6709
Max Act: 7.3584. Min Act: -0.1700
Data Index: 2829759 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6709. Min Range: -7.6709
Max Act: 7.2647. Min Act: -0.1700
Data Index: 7668175 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6709. Min Range: -7.6709
Max Act: 7.2334. Min Act: -0.1700
Data Index: 2709102 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6709. Min Range: -7.6709
Max Act: 7.2022. Min Act: -0.1700
Data Index: 8047896 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6709. Min Range: -7.6709
Max Act: 7.2022. Min Act: -0.1700
Data Index: 3210061 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6709. Min Range: -7.6709
Max Act: 7.1397. Min Act: -0.1700
Data Index: 5670591 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6709. Min Range: -7.6709
Max Act: 7.1084. Min Act: -0.1700
Data Index: 1250739 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6709. Min Range: -7.6709
Max Act: 7.0772. Min Act: -0.1700
Data Index: 5506305 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6709. Min Range: -7.6709
Max Act: 7.0772. Min Act: -0.1700
Data Index: 5873821 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6709. Min Range: -7.6709
Max Act: 7.0772. Min Act: -0.1700
Data Index: 4323353 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6709. Min Range: -7.6709
Max Act: 7.0459. Min Act: -0.1700
Data Index: 6094 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6709. Min Range: -7.6709
Max Act: 7.0459. Min Act: -0.1700
Data Index: 946579 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6709. Min Range: -7.6709
Max Act: 7.0147. Min Act: -0.1700
Data Index: 4106959 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6709. Min Range: -7.6709
Max Act: 7.0459. Min Act: -0.1700
Data Index: 3945452 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6709. Min Range: -7.6709
Max Act: 7.0772. Min Act: -0.1700
Data Index: 1621096 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6709. Min Range: -7.6709
Max Act: 7.0147. Min Act: -0.1700
Data Index: 5242053 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #19