Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1795 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6082. Min Range: -5.6082
Max Act: 5.6082. Min Act: -0.1700
Data Index: 466759 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6082. Min Range: -5.6082
Max Act: 5.5145. Min Act: -0.1700
Data Index: 5667400 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6082. Min Range: -5.6082
Max Act: 5.4520. Min Act: -0.1700
Data Index: 7698951 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6082. Min Range: -5.6082
Max Act: 5.4832. Min Act: -0.1700
Data Index: 1556606 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6082. Min Range: -5.6082
Max Act: 5.3895. Min Act: -0.1700
Data Index: 4755083 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6082. Min Range: -5.6082
Max Act: 5.4207. Min Act: -0.1700
Data Index: 7846737 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6082. Min Range: -5.6082
Max Act: 5.3582. Min Act: -0.1700
Data Index: 1769857 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6082. Min Range: -5.6082
Max Act: 5.3270. Min Act: -0.1700
Data Index: 912825 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6082. Min Range: -5.6082
Max Act: 5.2957. Min Act: -0.1700
Data Index: 1783198 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6082. Min Range: -5.6082
Max Act: 5.2957. Min Act: -0.1700
Data Index: 4712753 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6082. Min Range: -5.6082
Max Act: 5.2957. Min Act: -0.1700
Data Index: 8515963 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6082. Min Range: -5.6082
Max Act: 5.2957. Min Act: -0.1700
Data Index: 3515767 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6082. Min Range: -5.6082
Max Act: 5.2645. Min Act: -0.1700
Data Index: 8737400 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6082. Min Range: -5.6082
Max Act: 5.2332. Min Act: -0.1700
Data Index: 1130029 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6082. Min Range: -5.6082
Max Act: 5.2645. Min Act: -0.1700
Data Index: 3685880 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6082. Min Range: -5.6082
Max Act: 5.2332. Min Act: -0.1700
Data Index: 3534882 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6082. Min Range: -5.6082
Max Act: 5.2332. Min Act: -0.1700
Data Index: 7634773 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6082. Min Range: -5.6082
Max Act: 5.2332. Min Act: -0.1700
Data Index: 6776319 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6082. Min Range: -5.6082
Max Act: 5.2332. Min Act: -0.1700
Data Index: 7906533 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6082. Min Range: -5.6082
Max Act: 5.2020. Min Act: -0.1700
Data Index: 7483040 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #19