Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4954 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.3179. Min Range: -4.3179
Max Act: 4.3179. Min Act: -0.1700
Data Index: 4584337 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3179. Min Range: -4.3179
Max Act: 4.3179. Min Act: -0.1700
Data Index: 4584324 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3179. Min Range: -4.3179
Max Act: 4.2866. Min Act: -0.1700
Data Index: 2624964 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3179. Min Range: -4.3179
Max Act: 4.2866. Min Act: -0.1700
Data Index: 3976413 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3179. Min Range: -4.3179
Max Act: 4.2866. Min Act: -0.1700
Data Index: 1272235 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3179. Min Range: -4.3179
Max Act: 4.2241. Min Act: -0.1700
Data Index: 5144109 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3179. Min Range: -4.3179
Max Act: 4.2554. Min Act: -0.1700
Data Index: 3245112 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3179. Min Range: -4.3179
Max Act: 4.2554. Min Act: -0.1700
Data Index: 5368455 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3179. Min Range: -4.3179
Max Act: 4.2554. Min Act: -0.1699
Data Index: 3467223 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3179. Min Range: -4.3179
Max Act: 4.2554. Min Act: -0.1700
Data Index: 2467387 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3179. Min Range: -4.3179
Max Act: 4.2554. Min Act: -0.1700
Data Index: 5529498 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3179. Min Range: -4.3179
Max Act: 4.2554. Min Act: -0.1699
Data Index: 753611 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3179. Min Range: -4.3179
Max Act: 4.2554. Min Act: -0.1697
Data Index: 2599990 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3179. Min Range: -4.3179
Max Act: 4.2554. Min Act: -0.1700
Data Index: 7412762 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3179. Min Range: -4.3179
Max Act: 4.2554. Min Act: -0.1700
Data Index: 1025327 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3179. Min Range: -4.3179
Max Act: 4.2241. Min Act: -0.1700
Data Index: 2624963 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3179. Min Range: -4.3179
Max Act: 4.2554. Min Act: -0.1700
Data Index: 1323174 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3179. Min Range: -4.3179
Max Act: 4.2554. Min Act: -0.1700
Data Index: 3923937 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3179. Min Range: -4.3179
Max Act: 4.2554. Min Act: -0.1700
Data Index: 1463703 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3179. Min Range: -4.3179
Max Act: 4.2554. Min Act: -0.1700
Data Index: 4263958 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #19