Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3051 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1205. Min Range: -6.1205
Max Act: 6.1205. Min Act: -0.1700
Data Index: 2229572 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1205. Min Range: -6.1205
Max Act: 6.0268. Min Act: -0.1700
Data Index: 8514400 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1205. Min Range: -6.1205
Max Act: 5.8705. Min Act: -0.1700
Data Index: 1591499 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1205. Min Range: -6.1205
Max Act: 5.8080. Min Act: -0.1700
Data Index: 3024904 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1205. Min Range: -6.1205
Max Act: 5.8393. Min Act: -0.1700
Data Index: 4168832 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1205. Min Range: -6.1205
Max Act: 5.8080. Min Act: -0.1700
Data Index: 7357506 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1205. Min Range: -6.1205
Max Act: 5.7768. Min Act: -0.1700
Data Index: 462144 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1205. Min Range: -6.1205
Max Act: 5.7455. Min Act: -0.1700
Data Index: 5483860 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1205. Min Range: -6.1205
Max Act: 5.7455. Min Act: -0.1700
Data Index: 239996 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1205. Min Range: -6.1205
Max Act: 5.6830. Min Act: -0.1700
Data Index: 4004915 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1205. Min Range: -6.1205
Max Act: 5.6830. Min Act: -0.1700
Data Index: 2966789 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1205. Min Range: -6.1205
Max Act: 5.6830. Min Act: -0.1700
Data Index: 6072539 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1205. Min Range: -6.1205
Max Act: 5.6518. Min Act: -0.1700
Data Index: 404706 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1205. Min Range: -6.1205
Max Act: 5.6205. Min Act: -0.1700
Data Index: 689606 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1205. Min Range: -6.1205
Max Act: 5.5893. Min Act: -0.1700
Data Index: 2188963 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1205. Min Range: -6.1205
Max Act: 5.5580. Min Act: -0.1700
Data Index: 259530 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1205. Min Range: -6.1205
Max Act: 5.5580. Min Act: -0.1700
Data Index: 5961026 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1205. Min Range: -6.1205
Max Act: 5.5268. Min Act: -0.1700
Data Index: 8219255 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1205. Min Range: -6.1205
Max Act: 5.5268. Min Act: -0.1700
Data Index: 2979556 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1205. Min Range: -6.1205
Max Act: 5.4955. Min Act: -0.1700
Data Index: 4505059 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19