Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3360 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3675. Min Range: -7.3675
Max Act: 7.3675. Min Act: -0.1700
Data Index: 5056223 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3675. Min Range: -7.3675
Max Act: 7.2737. Min Act: -0.1700
Data Index: 5056207 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3675. Min Range: -7.3675
Max Act: 7.0862. Min Act: -0.1700
Data Index: 5345779 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3675. Min Range: -7.3675
Max Act: 6.9925. Min Act: -0.1700
Data Index: 1842043 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3675. Min Range: -7.3675
Max Act: 6.9612. Min Act: -0.1700
Data Index: 206265 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3675. Min Range: -7.3675
Max Act: 6.9612. Min Act: -0.1700
Data Index: 4125980 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3675. Min Range: -7.3675
Max Act: 6.9300. Min Act: -0.1700
Data Index: 6302324 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3675. Min Range: -7.3675
Max Act: 6.9300. Min Act: -0.1700
Data Index: 6331903 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3675. Min Range: -7.3675
Max Act: 6.8987. Min Act: -0.1700
Data Index: 8207636 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3675. Min Range: -7.3675
Max Act: 6.8362. Min Act: -0.1700
Data Index: 8338400 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3675. Min Range: -7.3675
Max Act: 6.8362. Min Act: -0.1700
Data Index: 7990285 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3675. Min Range: -7.3675
Max Act: 6.8362. Min Act: -0.1700
Data Index: 7885378 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3675. Min Range: -7.3675
Max Act: 6.8362. Min Act: -0.1700
Data Index: 8617104 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3675. Min Range: -7.3675
Max Act: 6.8050. Min Act: -0.1700
Data Index: 4990003 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3675. Min Range: -7.3675
Max Act: 6.8050. Min Act: -0.1700
Data Index: 1316092 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3675. Min Range: -7.3675
Max Act: 6.7425. Min Act: -0.1700
Data Index: 3311428 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3675. Min Range: -7.3675
Max Act: 6.7425. Min Act: -0.1700
Data Index: 3927462 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3675. Min Range: -7.3675
Max Act: 6.7425. Min Act: -0.1700
Data Index: 6782632 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3675. Min Range: -7.3675
Max Act: 6.7112. Min Act: -0.1700
Data Index: 8207637 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3675. Min Range: -7.3675
Max Act: 6.6487. Min Act: -0.1700
Data Index: 7999438 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #19