Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2787 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3206. Min Range: -5.3206
Max Act: 5.3206. Min Act: -0.1700
Data Index: 1518926 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3206. Min Range: -5.3206
Max Act: 5.2268. Min Act: -0.1700
Data Index: 7595158 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3206. Min Range: -5.3206
Max Act: 5.1956. Min Act: -0.1700
Data Index: 6757934 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3206. Min Range: -5.3206
Max Act: 5.1643. Min Act: -0.1700
Data Index: 6545177 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3206. Min Range: -5.3206
Max Act: 5.1956. Min Act: -0.1700
Data Index: 37602 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3206. Min Range: -5.3206
Max Act: 5.1643. Min Act: -0.1700
Data Index: 4475954 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3206. Min Range: -5.3206
Max Act: 5.1956. Min Act: -0.1700
Data Index: 4448239 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3206. Min Range: -5.3206
Max Act: 5.1331. Min Act: -0.1700
Data Index: 6978171 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3206. Min Range: -5.3206
Max Act: 5.1331. Min Act: -0.1700
Data Index: 6349454 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3206. Min Range: -5.3206
Max Act: 5.1331. Min Act: -0.1700
Data Index: 2486981 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3206. Min Range: -5.3206
Max Act: 5.1331. Min Act: -0.1700
Data Index: 3837411 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3206. Min Range: -5.3206
Max Act: 5.1018. Min Act: -0.1700
Data Index: 5570385 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3206. Min Range: -5.3206
Max Act: 5.1018. Min Act: -0.1700
Data Index: 3136482 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3206. Min Range: -5.3206
Max Act: 5.1331. Min Act: -0.1700
Data Index: 6811032 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3206. Min Range: -5.3206
Max Act: 5.1018. Min Act: -0.1700
Data Index: 7940990 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3206. Min Range: -5.3206
Max Act: 5.1018. Min Act: -0.1700
Data Index: 745600 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3206. Min Range: -5.3206
Max Act: 5.1018. Min Act: -0.1700
Data Index: 8573933 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3206. Min Range: -5.3206
Max Act: 5.1018. Min Act: -0.1700
Data Index: 2624716 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3206. Min Range: -5.3206
Max Act: 5.0706. Min Act: -0.1700
Data Index: 1001753 (Open Web Text)
Max Activating Token Index: 53
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3206. Min Range: -5.3206
Max Act: 5.0706. Min Act: -0.1700
Data Index: 6444876 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19