Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3612 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8947. Min Range: -8.8947
Max Act: 8.8947. Min Act: -0.1700
Data Index: 371347 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8947. Min Range: -8.8947
Max Act: 8.4572. Min Act: -0.1700
Data Index: 4215016 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8947. Min Range: -8.8947
Max Act: 8.3322. Min Act: -0.1700
Data Index: 5249554 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8947. Min Range: -8.8947
Max Act: 8.3322. Min Act: -0.1700
Data Index: 5236523 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8947. Min Range: -8.8947
Max Act: 8.2072. Min Act: -0.1700
Data Index: 755024 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8947. Min Range: -8.8947
Max Act: 8.2072. Min Act: -0.1700
Data Index: 382300 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8947. Min Range: -8.8947
Max Act: 8.1447. Min Act: -0.1700
Data Index: 7895718 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8947. Min Range: -8.8947
Max Act: 8.0822. Min Act: -0.1700
Data Index: 1592810 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8947. Min Range: -8.8947
Max Act: 8.0822. Min Act: -0.1700
Data Index: 6692245 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8947. Min Range: -8.8947
Max Act: 8.0197. Min Act: -0.1700
Data Index: 116284 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8947. Min Range: -8.8947
Max Act: 7.8947. Min Act: -0.1700
Data Index: 3693670 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8947. Min Range: -8.8947
Max Act: 7.9572. Min Act: -0.1700
Data Index: 5678758 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8947. Min Range: -8.8947
Max Act: 7.9572. Min Act: -0.1700
Data Index: 2428098 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8947. Min Range: -8.8947
Max Act: 7.9572. Min Act: -0.1700
Data Index: 2112793 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8947. Min Range: -8.8947
Max Act: 7.8947. Min Act: -0.1700
Data Index: 8408699 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8947. Min Range: -8.8947
Max Act: 7.8947. Min Act: -0.1700
Data Index: 1925327 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8947. Min Range: -8.8947
Max Act: 7.8322. Min Act: -0.1700
Data Index: 6987945 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8947. Min Range: -8.8947
Max Act: 7.8322. Min Act: -0.1700
Data Index: 5249552 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8947. Min Range: -8.8947
Max Act: 7.8322. Min Act: -0.1700
Data Index: 5899639 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8947. Min Range: -8.8947
Max Act: 7.8322. Min Act: -0.1700
Data Index: 700042 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #19