Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2097 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.8268. Min Range: -1.8268
Max Act: 1.8268. Min Act: -0.1700
Data Index: 3371416 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.8268. Min Range: -1.8268
Max Act: 1.8182. Min Act: -0.1700
Data Index: 4702352 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.8268. Min Range: -1.8268
Max Act: 1.8010. Min Act: -0.1700
Data Index: 5092079 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.8268. Min Range: -1.8268
Max Act: 1.7838. Min Act: -0.1700
Data Index: 8215266 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.8268. Min Range: -1.8268
Max Act: 1.7924. Min Act: -0.1700
Data Index: 3344540 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.8268. Min Range: -1.8268
Max Act: 1.7666. Min Act: -0.1700
Data Index: 6106959 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.8268. Min Range: -1.8268
Max Act: 1.7579. Min Act: -0.1700
Data Index: 2814023 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.8268. Min Range: -1.8268
Max Act: 1.7579. Min Act: -0.1700
Data Index: 7706009 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.8268. Min Range: -1.8268
Max Act: 1.7493. Min Act: -0.1700
Data Index: 7602148 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.8268. Min Range: -1.8268
Max Act: 1.7407. Min Act: -0.1700
Data Index: 4226062 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.8268. Min Range: -1.8268
Max Act: 1.7320. Min Act: -0.1700
Data Index: 286714 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.8268. Min Range: -1.8268
Max Act: 1.7320. Min Act: -0.1700
Data Index: 7908954 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.8268. Min Range: -1.8268
Max Act: 1.7320. Min Act: -0.1700
Data Index: 5539296 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.8268. Min Range: -1.8268
Max Act: 1.7234. Min Act: -0.1700
Data Index: 819033 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.8268. Min Range: -1.8268
Max Act: 1.7147. Min Act: -0.1700
Data Index: 4396300 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.8268. Min Range: -1.8268
Max Act: 1.7147. Min Act: -0.1700
Data Index: 688119 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.8268. Min Range: -1.8268
Max Act: 1.7060. Min Act: -0.1700
Data Index: 4497464 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.8268. Min Range: -1.8268
Max Act: 1.7060. Min Act: -0.1700
Data Index: 5593902 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.8268. Min Range: -1.8268
Max Act: 1.6974. Min Act: -0.1700
Data Index: 1680651 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.8268. Min Range: -1.8268
Max Act: 1.6974. Min Act: -0.1700
Data Index: 5069932 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19